© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4542
    Prev
    Next
    INDEX
    Explanations

    code snippets, likely in Python or Javascript, containing keywords like 'def', 'const', 'function', 'api', 'update', 'config'

    oai_token-act-pair · gemini-2.0-flash

    start of words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     estekak
    -0.81
     JpaRepository
    -0.76
     виправивши
    -0.71
    TagMode
    -0.69
     فريبيس
    -0.63
    MigrationBuilder
    -0.60
     Roskov
    -0.59
    fromnode
    -0.57
    */),
    -0.56
    TestingModule
    -0.53
    POSITIVE LOGITS
    <bos>
    0.58
    pase
    0.50
    tencent
    0.47
    liga
    0.46
    hely
    0.45
    ifolium
    0.45
     i
    0.44
    ebi
    0.43
     yii
    0.43
    rei
    0.42
    Activations Density 21.177%

    No Known Activations