© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34214
    Prev
    Next
    INDEX
    Explanations

    preference questions

    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_7_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
     are
    1.90
     in
    1.61
     is
    1.59
     be
    1.38
     as
    1.33
    在
    1.31
     at
    1.29
     of
    1.27
    ية
    1.22
    க
    1.22
    POSITIVE LOGITS
     carène
    0.89
    SCF
    0.89
    ULE
    0.88
     datth
    0.84
    SR
    0.83
    UnityEngine
    0.82
     sacrament
    0.82
    Stats
    0.82
    SA
    0.81
    Functions
    0.81
    Activations Density 0.000%

    No Known Activations