© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199236
    Prev
    Next
    INDEX
    Explanations

    you

    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
    Ἔ
    0.44
     meny
    0.39
     ressemble
    0.38
     படி
    0.37
     αι
    0.36
    匱
    0.35
     निः
    0.35
     უფ
    0.35
     ਭ
    0.35
    illow
    0.35
    POSITIVE LOGITS
     साहब
    0.41
    Deps
    0.40
    trx
    0.39
    Sq
    0.37
    rx
    0.37
     Taq
    0.37
    Expr
    0.36
    marshall
    0.36
    Wa
    0.36
    uu
    0.36
    Activations Density 0.006%

    No Known Activations