© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12871
    Prev
    Next
    INDEX
    Explanations

    call me

    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_40_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
    WIL
    0.45
    🛡
    0.41
     habitat
    0.38
    ready
    0.37
    Habitat
    0.36
    Administration
    0.36
    Arche
    0.36
    Wil
    0.36
    ラック
    0.36
     Wilber
    0.35
    POSITIVE LOGITS
     нужны
    0.50
    istungs
    0.46
     প্রয়োজন
    0.41
     Locomotive
    0.39
     Loco
    0.38
    占
    0.38
     പറയ
    0.38
    калә
    0.38
     gust
    0.37
     Eliot
    0.37
    Activations Density 0.000%

    No Known Activations