© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5767
    Prev
    Next
    INDEX
    Explanations

    HTML code defining data attributes and dashboard elements

    oai_token-act-pair · gemini-2.0-flash

    data

    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
     FR
    -0.50
    HasForeignKey
    -0.49
     p
    -0.48
    ReusableCell
    -0.46
    WriteLiteral
    -0.46
    createClass
    -0.45
    FR
    -0.44
     fr
    -0.42
     m
    -0.42
    CppMethod
    -0.42
    POSITIVE LOGITS
     TextInputType
    0.78
     myſelf
    0.75
     tranſ
    0.69
     متعلقه
    0.67
     juſt
    0.67
     فريبيس
    0.66
     uſe
    0.66
    Spoljašnje
    0.65
     ſche
    0.61
     gabri
    0.61
    Activations Density 0.515%

    No Known Activations