© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206265
    Prev
    Next
    INDEX
    Explanations

    color-coding

    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_10_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
    \
    0.81
     uten
    0.77
     in
    0.77
     ar
    0.76
     OE
    0.75
     und
    0.73
     utan
    0.73
     ard
    0.73
     vein
    0.72
     der
    0.71
    POSITIVE LOGITS
    𝗴
    0.91
    directory
    0.84
    group
    0.83
    bedrooms
    0.83
    boxes
    0.77
    مة
    0.77
    fallback
    0.77
    estados
    0.76
    مح
    0.72
    grown
    0.71
    Activations Density 0.005%

    No Known Activations