© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2011
    Prev
    Next
    INDEX
    Explanations

    code fragments with comments and keywords related to testing and memory allocation

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.75
    ьаж
    -0.62
    idać
    -0.57
     كومونز
    -0.57
    łby
    -0.56
    middels
    -0.54
    StoreMessageInfo
    -0.54
    /***/
    -0.50
    tamment
    -0.50
    AsUp
    -0.50
    POSITIVE LOGITS
     صوتيه
    0.60
    DeleteBehavior
    0.59
    FormTagHelper
    0.57
     Controls
    0.55
    DebuggerNonUser
    0.53
    ChildScrollView
    0.53
     שלי
    0.52
    τώ
    0.52
    QtWidgets
    0.52
    rats
    0.50
    Activations Density 10.527%

    No Known Activations