© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113116
    Prev
    Next
    INDEX
    Explanations

    newer versions, models, drivers

    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_2_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
    1.71
    '
    1.23
     synergies
    1.22
     zmiany
    1.21
     incisions
    1.20
     utterances
    1.18
    ﺍ
    1.18
     supergiants
    1.16
    {
    1.12
     ambitions
    1.11
    POSITIVE LOGITS
    с
    1.48
    un
    1.19
    a
    1.16
    present
    1.13
    க்கு
    1.09
    го
    1.09
    lehem
    1.07
    am
    1.04
    ktiv
    1.03
    on
    1.02
    Activations Density 0.000%

    No Known Activations