© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199359
    Prev
    Next
    INDEX
    Explanations

    correlation or tail risk

    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_12_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
    UC
    0.48
     chisel
    0.47
     ד
    0.45
    唄
    0.45
    ENE
    0.43
    UTA
    0.43
    UB
    0.42
     ड
    0.42
    }<
    0.42
    鉗
    0.42
    POSITIVE LOGITS
    be
    0.61
     thermost
    0.52
    ť
    0.50
    يني
    0.50
    लु
    0.50
     மணிக்கு
    0.50
    ang
    0.50
    ার্ভ
    0.50
    لاك
    0.49
    籠
    0.49
    Activations Density 0.017%

    No Known Activations