© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11948
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs related to permission or possibility

    oai_token-act-pair · gemini-2.0-flash

    modal verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Билгалдахарш
    -0.73
    новниш
    -0.72
    kháu
    -0.66
    ModelAdmin
    -0.61
    tagext
    -0.61
    Референце
    -0.59
    migrationBuilder
    -0.59
    couverture
    -0.59
     Púb
    -0.56
    новништво
    -0.56
    POSITIVE LOGITS
    Personensuche
    0.49
     me
    0.48
     Land
    0.46
     void
    0.46
     responsible
    0.46
    Fprintf
    0.45
     missing
    0.44
     required
    0.44
     the
    0.43
    SizeMode
    0.43
    Activations Density 1.536%

    No Known Activations