© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89907
    Prev
    Next
    INDEX
    Explanations

    supports feature/capability

    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
    n
    0.43
    h
    0.43
    t
    0.40
    p
    0.39
    us
    0.38
    et
    0.36
    v
    0.34
    nél
    0.32
    á
    0.32
    ër
    0.31
    POSITIVE LOGITS
     upstairs
    0.31
     whispers
    0.30
    गरानी
    0.30
     refurb
    0.29
     bares
    0.29
     trivially
    0.29
     blockchain
    0.29
     recuperar
    0.29
     постро
    0.28
     determina
    0.28
    Activations Density 0.019%

    No Known Activations