© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80927
    Prev
    Next
    INDEX
    Explanations

    known for

    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_31_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
    Fres
    0.41
    followers
    0.39
     Fres
    0.38
     affiliation
    0.38
    ᆭ
    0.37
     Followers
    0.37
     followers
    0.36
     furnishings
    0.34
     CCSDT
    0.34
    Partner
    0.34
    POSITIVE LOGITS
     inflex
    0.39
    hing
    0.36
     inflammation
    0.33
     Inflammation
    0.33
    橛
    0.33
     intended
    0.32
    cible
    0.32
     infl
    0.32
    intended
    0.32
    枃
    0.31
    Activations Density 0.004%

    No Known Activations