© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195614
    Prev
    Next
    INDEX
    Explanations

    scarab beetles

    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_4_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
     was
    0.18
    াব
    0.15
    '
    0.15
     are
    0.15
    "
    0.13
    ht
    0.13
    }{
    0.13
    ene
    0.13
     at
    0.13
    お客様
    0.13
    POSITIVE LOGITS
    er
    0.25
    en
    0.22
    i
    0.22
    y
    0.22
    ي
    0.19
    ar
    0.18
    is
    0.18
    e
    0.18
    el
    0.18
    يها
    0.18
    Activations Density 0.001%

    No Known Activations