© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10438
    Prev
    Next
    INDEX
    Explanations

    fine-tune

    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_40_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
     rgba
    0.36
     मरा
    0.36
    ---|
    0.33
    rrbracket
    0.33
     meditation
    0.32
    ুল্লাহ
    0.32
     ens
    0.32
     Cod
    0.32
     Kumb
    0.32
    忍者
    0.31
    POSITIVE LOGITS
     fine
    2.42
    Fine
    2.27
     Fine
    2.17
    fine
    2.14
     FINE
    1.98
    FINE
    1.81
    细
    1.49
    細
    1.48
     fines
    1.38
     finer
    1.38
    Activations Density 0.309%

    No Known Activations