© 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-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121853
    Prev
    Next
    INDEX
    Explanations

    column, 2, inside

    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_38_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
    bald
    0.41
    Sto
    0.36
     WER
    0.35
    嵓
    0.34
     средства
    0.34
    ີ່
    0.34
    uvat
    0.33
    erald
    0.33
    徃
    0.33
    ilarly
    0.32
    POSITIVE LOGITS
     XNUMX
    0.39
    Ϳ
    0.39
    ⟋
    0.38
     روستا
    0.37
    ަށް
    0.37
     snowflakes
    0.35
    ची
    0.34
    ...),
    0.34
    ობაში
    0.33
     🙂
    0.33
    Activations Density 0.109%

    No Known Activations