© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157289
    Prev
    Next
    INDEX
    Explanations

    niezależny / independent

    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_2_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
    1.34
     في
    1.23
    d
    1.23
     ي
    1.08
    ים
    1.05
     on
    1.02
     الل
    1.00
    elijke
    1.00
     osoba
    0.99
    dade
    0.98
    POSITIVE LOGITS
    н
    1.70
    ن
    1.63
    น
    1.55
    ν
    1.31
    นิด
    1.27
    ন
    1.26
    EB
    1.22
    مه
    1.19
    ン
    1.19
    νε
    1.18
    Activations Density 0.000%

    No Known Activations