© 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. 229163
    Prev
    Next
    INDEX
    Explanations

    string type

    np_max-act-logits · gemini-2.5-flash-lite
    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
    㠻
    0.41
     Once
    0.37
    ੋਂ
    0.36
    ঞ্জন
    0.35
    ારે
    0.35
     Marie
    0.35
     Thirteen
    0.35
     RegExp
    0.34
    られている
    0.34
     MyApplication
    0.34
    POSITIVE LOGITS
    🧧
    0.41
     ليك
    0.37
     व्हाट
    0.37
    ュ
    0.37
     repl
    0.36
     radial
    0.36
    umin
    0.35
    మ
    0.35
     penetrating
    0.35
    FAC
    0.35
    Activations Density 0.005%

    No Known Activations