© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229340
    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_57_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
    に出
    0.38
     lor
    0.38
    Reading
    0.37
    读
    0.37
    Que
    0.36
     Reunion
    0.36
    മെ
    0.36
    Laur
    0.36
     bunlar
    0.36
     வேல
    0.36
    POSITIVE LOGITS
    ｐ
    0.39
     dajj
    0.38
    чить
    0.38
     canoes
    0.38
     nozzles
    0.37
    দ্দিক
    0.37
     télé
    0.36
     paddles
    0.36
    stoi
    0.36
     [§
    0.35
    Activations Density 0.000%

    No Known Activations