© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7344
    Prev
    Next
    INDEX
    Explanations

    instances of authorities, governing bodies, or actions that require some kind of permission or compliance.

    oai_token-act-pair · gemini-2.0-flash

    words related to counter-terrorism and security

    np_token-act-pair-logits · gpt-4o-mini

    need for something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Климат
    -0.57
    WarningLevel
    -0.52
    AutoField
    -0.49
    npmjs
    -0.42
    fromnode
    -0.41
    WithIdentifier
    -0.39
     parcialmente
    -0.39
     Partially
    -0.38
    kembangan
    -0.36
    rowad
    -0.36
    POSITIVE LOGITS
     predictability
    0.71
     Efq
    0.69
    */),
    0.67
     '\\;'
    0.66
    Viitteet
    0.66
    ]--;
    0.66
     alignment
    0.64
     calendriers
    0.64
     adequate
    0.63
    LookAnd
    0.63
    Activations Density 3.182%

    No Known Activations