© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123625
    Prev
    Next
    INDEX
    Explanations

    dead end

    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_37_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
    functions
    0.46
    covariance
    0.42
    賚
    0.42
    custom
    0.41
    marco
    0.41
     للك
    0.40
     marcos
    0.38
     Functions
    0.38
    freeze
    0.38
     επέ
    0.37
    POSITIVE LOGITS
     dead
    0.98
     blind
    0.93
     cul
    0.91
     Dead
    0.84
     alleys
    0.73
    盲
    0.73
     DEAD
    0.72
     Cul
    0.71
    Dead
    0.71
     Blind
    0.71
    Activations Density 0.002%

    No Known Activations