© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200315
    Prev
    Next
    INDEX
    Explanations

    seafood

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     scratched
    0.44
     Gebrauch
    0.42
    হাম্ম
    0.40
     Aank
    0.40
     scratch
    0.40
     scrat
    0.38
    ຮ
    0.38
    喏
    0.38
    ᑉ
    0.38
     Scratch
    0.38
    POSITIVE LOGITS
    Aid
    0.41
    forward
    0.40
    sma
    0.40
     rotations
    0.38
    --");
    0.38
     shears
    0.38
    sid
    0.38
    suppliers
    0.38
     Aid
    0.37
    Attempts
    0.36
    Activations Density 0.001%

    No Known Activations