© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261595
    Prev
    Next
    INDEX
    Explanations

    date-fns or ISO date formatting

    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_22_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
    regional
    0.48
    सन्
    0.45
    Bau
    0.43
    विदेश
    0.43
    棲
    0.43
    seit
    0.43
    foto
    0.42
     Desde
    0.42
     منذ
    0.41
    siz
    0.41
    POSITIVE LOGITS
     consentement
    0.49
     unui
    0.42
     bushel
    0.42
     soapy
    0.42
    ("",
    0.41
     savon
    0.41
     यामुळे
    0.41
     bus
    0.40
    愠
    0.40
     spells
    0.40
    Activations Density 0.000%

    No Known Activations