© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167481
    Prev
    Next
    INDEX
    Explanations

    param

    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_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
    /****
    0.42
    --"
    0.40
     напи
    0.39
    शुदा
    0.38
    neux
    0.38
    public
    0.37
    ্যাট
    0.36
    ✉
    0.36
    //$
    0.35
    <blockquote>
    0.35
    POSITIVE LOGITS
     }*/
    0.37
     actively
    0.36
    </caption>
    0.36
     gou
    0.36
    積極
    0.36
    カイブ
    0.36
    ামীর
    0.35
    ”
    0.35
    墳
    0.35
    ”)
    0.34
    Activations Density 0.000%

    No Known Activations