© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13969
    Prev
    Next
    INDEX
    Explanations

    the substring "IN", often occurring in code snippets

    oai_token-act-pair · gemini-2.0-flash

    variations of the token 'IN'

    np_token-act-pair-logits · gpt-4o-mini

    Code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    DialogContent
    -0.62
     AssemblyCompany
    -0.54
    LookAnd
    -0.52
    </thead>
    -0.52
    MigrationBuilder
    -0.50
    assertj
    -0.49
    XmlAccessorType
    -0.48
     NSCoder
    -0.48
    IntoConstraints
    -0.48
    chito
    -0.47
    POSITIVE LOGITS
     nawr
    0.58
    uclear
    0.54
    orth
    0.52
     tartalomajánló
    0.51
    jonen
    0.50
    évaluateur
    0.49
     phê
    0.49
     zvuky
    0.48
     autorytatywna
    0.48
     rowCount
    0.47
    Activations Density 1.427%

    No Known Activations