© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10486
    Prev
    Next
    INDEX
    Explanations

    words indicating family relationships or proper names

    oai_token-act-pair · gemini-2.0-flash

    family relations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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>
    -1.16
    mybatisplus
    -0.73
     HttpNotFound
    -0.63
     nakalista
    -0.56
    ibol
    -0.55
    Soorten
    -0.53
    bootstrapcdn
    -0.50
    ]=>
    -0.49
    peq
    -0.49
    Eglise
    -0.48
    POSITIVE LOGITS
     useStyles
    0.68
    Przypisy
    0.63
     ModelExpression
    0.63
    ViewFeatures
    0.62
    Bronnen
    0.62
     "..\..\
    0.59
     Préférences
    0.58
     "..\..\..\
    0.58
    DebuggerNonUser
    0.57
    queryInterface
    0.56
    Activations Density 0.611%

    No Known Activations