© 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. 11852
    Prev
    Next
    INDEX
    Explanations

    the string "Kar"

    oai_token-act-pair · gemini-2.0-flash

    Kar/Ker

    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
     double
    -0.48
    катери
    -0.46
    щина
    -0.43
    istoitu
    -0.42
    featureID
    -0.42
     car
    -0.41
    ردد
    -0.41
     Carter
    -0.40
     App
    -0.40
     app
    -0.40
    POSITIVE LOGITS
     مشين
    0.98
     تضيفلها
    0.82
    :+:
    0.75
     createState
    0.73
    </thead>
    0.71
     ferons
    0.67
     dignité
    0.66
    __":
    0.65
     bonté
    0.65
     dieux
    0.63
    Activations Density 0.458%

    No Known Activations