© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15250
    Prev
    Next
    INDEX
    Explanations

    information about news or reports

    oai_token-act-pair · gemini-2.0-flash

    reports rumors information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    :✨
    -0.78
    ArrowToggle
    -0.73
    +#+#
    -0.69
    RTEE
    -0.69
     Infórmanos
    -0.68
    rrggbb
    -0.68
    bitField
    -0.68
    XmlAccessorType
    -0.67
    CppMethod
    -0.66
    ViewFeatures
    -0.66
    POSITIVE LOGITS
     carried
    0.49
    iprot
    0.47
    upaten
    0.46
     doing
    0.46
     Sheldon
    0.45
     pour
    0.44
     carrying
    0.44
    scriptcase
    0.43
     cellspacing
    0.43
    apuram
    0.42
    Activations Density 0.973%

    No Known Activations