© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132859
    Prev
    Next
    INDEX
    Explanations

    Books

    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_50_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
     House
    0.44
    House
    0.43
     Wala
    0.43
    house
    0.43
    Ｗ
    0.42
    Wall
    0.42
    W
    0.41
    وال
    0.40
    ewall
    0.40
    wall
    0.39
    POSITIVE LOGITS
     caud
    0.39
    setVerticalGroup
    0.37
    க்த
    0.37
    カルシ
    0.37
     elevate
    0.36
     khung
    0.36
     koost
    0.36
    צל
    0.36
    筐
    0.36
    Perspective
    0.35
    Activations Density 0.001%

    No Known Activations