© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193879
    Prev
    Next
    INDEX
    Explanations

    names ending in ia or er

    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_4_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
    م
    1.77
    t
    1.51
    ي
    1.51
    ק
    1.44
    м
    1.37
    it
    1.36
    ش
    1.35
    ye
    1.30
    ij
    1.23
    i
    1.23
    POSITIVE LOGITS
    ۰
    1.47
    ۔
    1.05
    ০
    1.05
    פר
    0.99
    وک
    0.98
    тера
    0.91
    ۹
    0.87
    кті
    0.87
    inę
    0.84
    ۸
    0.83
    Activations Density 0.000%

    No Known Activations