© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59442
    Prev
    Next
    INDEX
    Explanations

    conversation start/end

    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_11_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
    of
    0.66
    IV
    0.63
    MR
    0.62
    Batch
    0.61
    Equals
    0.59
    SR
    0.59
    quire
    0.59
    ${
    0.57
    Addr
    0.57
    Building
    0.57
    POSITIVE LOGITS
    ת
    0.76
    t
    0.74
     planeta
    0.64
     estrogen
    0.64
     sunscreen
    0.63
     progesterone
    0.63
     indulge
    0.62
     obscene
    0.62
     arenas
    0.61
     to
    0.61
    Activations Density 0.009%

    No Known Activations