© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167000
    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_56_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
     си
    0.43
     si
    0.32
    <unused23>
    0.32
    Си
    0.31
    راجع
    0.31
    ฎ
    0.31
     سی
    0.31
    𝘷
    0.30
    си
    0.30
     passing
    0.30
    POSITIVE LOGITS
    ann
    0.35
    ancen
    0.33
    annotate
    0.31
    াসহ
    0.30
    ancy
    0.29
    auc
    0.29
    arnish
    0.29
     важли
    0.29
    ан
    0.28
    ্যান
    0.28
    Activations Density 0.000%

    No Known Activations