© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165357
    Prev
    Next
    INDEX
    Explanations

    size (small, large, extra)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    )
    0.37
    }
    0.36
    </div>
    0.34
    M
    0.33
    $
    0.32
    Ö
    0.32
    </i>
    0.32
    Z
    0.32
    {
    0.31
    >
    0.31
    POSITIVE LOGITS
    privileged
    0.34
     повышен
    0.32
    😎
    0.31
     поэтому
    0.30
     ሽፋ
    0.30
     कानून
    0.30
     ጉ
    0.30
    ඒ
    0.30
    🔱
    0.29
     प्रवा
    0.29
    Activations Density 0.003%

    No Known Activations