© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38787
    Prev
    Next
    INDEX
    Explanations

    daily lives

    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
     persist
    0.64
     described
    0.57
     black
    0.57
     to
    0.56
     other
    0.55
     ή
    0.55
     in
    0.55
     via
    0.55
     general
    0.54
    ком
    0.54
    POSITIVE LOGITS
    洨
    0.55
    🍩
    0.53
    𝘿
    0.53
    __()
    0.52
    ్‌
    0.52
    ｾ
    0.52
    Ϳ
    0.51
    为大家
    0.51
    OfDay
    0.51
     Paston
    0.50
    Activations Density 0.000%

    No Known Activations