© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12898
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical documentation of various types

    oai_token-act-pair · gemini-2.0-flash

    checks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ConstraintMaker
    -0.61
     كومونز
    -0.58
     estekak
    -0.56
     חיצוניים
    -0.54
    DebuggerNonUser
    -0.52
    ScopeManager
    -0.52
     uncomment
    -0.51
     =>
    -0.50
    guilty
    -0.49
    IMPORTED
    -0.49
    POSITIVE LOGITS
    <bos>
    0.60
    AlterField
    0.56
    fony
    0.51
    initComponents
    0.50
    setDo
    0.47
    breos
    0.45
     pagkak
    0.44
    createForm
    0.43
    CreateModel
    0.43
    figsize
    0.43
    Activations Density 10.431%

    No Known Activations