© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11858
    Prev
    Next
    INDEX
    Explanations

    topic noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dist
    0.31
    dru
    0.31
     as
    0.30
    MEL
    0.29
    dans
    0.29
    d
    0.29
    tu
    0.29
    distribution
    0.29
    ty
    0.29
    لما
    0.28
    POSITIVE LOGITS
     Became
    0.29
     accuse
    0.29
     sợ
    0.29
     underestimate
    0.29
    ONDER
    0.29
     couper
    0.28
     ውጤ
    0.28
    <0x99>
    0.28
     overestimate
    0.28
     ወቅ
    0.28
    Activations Density 0.041%

    No Known Activations