© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3489
    Prev
    Next
    INDEX
    Explanations

    code requirements and dependencies

    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
    핏
    0.39
    阀
    0.38
    ᄄ
    0.38
     valve
    0.37
     விடு
    0.36
    скім
    0.36
     ठीक
    0.35
    หาก
    0.35
    樖
    0.35
     adaptations
    0.35
    POSITIVE LOGITS
    Requires
    0.67
    requires
    0.66
     compares
    0.65
     requires
    0.62
     Requires
    0.59
    Provides
    0.58
    matches
    0.57
    provides
    0.57
     Provides
    0.56
     требует
    0.56
    Activations Density 0.011%

    No Known Activations