© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202731
    Prev
    Next
    INDEX
    Explanations

    custom error validation

    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_12_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
    \
    0.61
    dan
    0.56
    son
    0.55
    nombre
    0.55
    阜
    0.49
    an
    0.49
    res
    0.48
    del
    0.47
    ies
    0.46
    den
    0.46
    POSITIVE LOGITS
    Ր
    0.54
     spasms
    0.51
     busses
    0.50
     విడుదల
    0.49
    ində
    0.49
    До
    0.49
     ડ
    0.49
     vías
    0.47
     зада
    0.47
    𝐓
    0.47
    Activations Density 0.003%

    No Known Activations