© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3698
    Prev
    Next
    INDEX
    Explanations

    language related to possibility or conjecture

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     envies
    -0.48
    extends
    -0.46
    isien
    -0.45
    ksen
    -0.45
     Ahor
    -0.43
    wai
    -0.42
    ))){
    -0.42
     finishes
    -0.42
    ubber
    -0.42
    zy
    -0.42
    POSITIVE LOGITS
    Попис
    0.79
     الرياضيه
    0.75
    vician
    0.63
    WriteBarrier
    0.63
    цезда
    0.60
    UrlResolution
    0.59
     GenerationType
    0.57
     ModelExpression
    0.57
    ★★★★☆
    0.57
    AddHtmlAttribute
    0.56
    Activations Density 0.619%

    No Known Activations