© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82649
    Prev
    Next
    INDEX
    Explanations

    emojis 😄

    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_0_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
     in
    1.63
    ิ
    1.39
    ம்
    1.25
     inoxidable
    1.24
    ния
    1.23
     placa
    1.22
     fiecare
    1.22
    ান
    1.20
    রি
    1.18
    ی
    1.18
    POSITIVE LOGITS
    t
    1.92
    (
    1.67
    是
    1.59
    de
    1.50
    tions
    1.41
    tes
    1.37
    was
    1.37
    Re
    1.34
    ll
    1.32
    los
    1.32
    Activations Density 0.002%

    No Known Activations