© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9928
    Prev
    Next
    INDEX
    Explanations

    words related to rules, laws, requirements, or commonly accepted standards

    oai_token-act-pair · gemini-2.0-flash

    legal, political requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Перейти
    -0.75
     Majefty
    -0.72
     impression
    -0.69
    aronder
    -0.69
     cref
    -0.69
     mandate
    -0.69
    itated
    -0.68
    UserScript
    -0.66
     Lég
    -0.66
     inseparable
    -0.66
    POSITIVE LOGITS
    __':
    0.47
    gnore
    0.46
    SuppressLint
    0.46
     nakalista
    0.46
    FailureListener
    0.45
     mar
    0.44
    resizingMask
    0.44
     be
    0.43
    
    0.41
     bem
    0.41
    Activations Density 13.173%

    No Known Activations