© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87083
    Prev
    Next
    INDEX
    Explanations

    HB3

    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_3_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
    \
    0.77
    is
    0.74
    at
    0.71
    stå
    0.68
    ktion
    0.65
    zes
    0.64
    (−
    0.64
    rester
    0.63
    thers
    0.63
    "，
    0.63
    POSITIVE LOGITS
    t
    0.80
    ючи
    0.73
    ן
    0.68
     mencion
    0.66
     luxuri
    0.66
     amass
    0.63
     transform
    0.62
     averigu
    0.62
     defraud
    0.61
    nX
    0.61
    Activations Density 0.004%

    No Known Activations