© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21846
    Prev
    Next
    INDEX
    Explanations

    say "q" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     К
    1.43
     K
    1.36
    kv
    1.20
     kw
    1.20
     kv
    1.20
     Kv
    1.17
    К
    1.16
     KV
    1.14
     Kw
    1.13
    к
    1.11
    POSITIVE LOGITS
     u
    0.82
     gu
    0.81
    ual
    0.77
    uent
    0.73
    uir
    0.71
    ue
    0.70
    uest
    0.70
     ui
    0.70
     Ou
    0.68
    uation
    0.68
    Activations Density 0.045%

    No Known Activations