© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103891
    Prev
    Next
    INDEX
    Explanations

    multiple generations

    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_1_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
    2
    1.74
    1
    1.66
     be
    1.56
    3
    1.55
    4
    1.52
    0
    1.41
     (
    1.38
    7
    1.30
    8
    1.28
    ة
    1.27
    POSITIVE LOGITS
    ↵
    1.51
     poplar
    0.98
     ROY
    0.97
     unfilled
    0.93
     ETFs
    0.92
     marshmallow
    0.92
     acetylation
    0.92
     banished
    0.92
     piezo
    0.90
     فشاں
    0.89
    Activations Density 0.001%

    No Known Activations