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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261281
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
    س
    1.27
    it
    1.27
    스
    1.23
    is
    1.16
    as
    1.16
    <0x80>
    1.15
    ме
    1.14
    os
    1.10
    ah
    1.03
    é
    1.02
    POSITIVE LOGITS
    ↵
    1.04
    that
    0.99
    .
    0.97
    ld
    0.90
     राह
    0.87
    Key
    0.83
    lds
    0.82
    </h3>
    0.77
    rtel
    0.77
    3
    0.76
    Activations Density 0.000%

    No Known Activations