© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10580
    Prev
    Next
    INDEX
    Explanations

    the string "res"

    oai_token-act-pair · gemini-2.0-flash

    Res

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    brenner
    -0.54
    ValueStyle
    -0.53
    himovic
    -0.52
     betweenstory
    -0.50
    ftagPool
    -0.48
    ########.
    -0.47
    ciences
    -0.46
     déclarations
    -0.46
     raso
    -0.46
     sür
    -0.45
    POSITIVE LOGITS
     AttributeSet
    0.88
    MigrationBuilder
    0.80
     NgModule
    0.66
    UserScript
    0.61
    UnusedPrivate
    0.59
    Portály
    0.56
    XmlAccessType
    0.54
    EndContext
    0.54
     StatefulWidget
    0.54
    providedIn
    0.54
    Activations Density 0.579%

    No Known Activations