© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196903
    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_26_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
     самы
    0.43
     maksimal
    0.42
    ვ
    0.42
    в
    0.42
     vong
    0.41
    หน้า
    0.41
    v
    0.41
    ك
    0.41
    ږ
    0.41
     etwa
    0.41
    POSITIVE LOGITS
    ुक्त
    0.40
    utth
    0.40
    oja
    0.40
    ার্জন
    0.39
    மையான
    0.39
    тпу
    0.38
    iempo
    0.38
    ctuaries
    0.38
    <unused19>
    0.37
    raisers
    0.37
    Activations Density 0.000%

    No Known Activations