© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33037
    Prev
    Next
    INDEX
    Explanations

    language specific characters

    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_31_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
    </table>
    0.41
     }{\
    0.38
    अफ
    0.38
     experiencia
    0.38
     подробно
    0.37
    )[[
    0.37
    丰富
    0.37
     kej
    0.37
     कक्क
    0.37
     aulas
    0.36
    POSITIVE LOGITS
    很难
    0.38
     Froome
    0.36
    負
    0.36
     froth
    0.36
    を含
    0.36
    尔多
    0.35
    负
    0.35
    agate
    0.34
     Salem
    0.34
    ore
    0.34
    Activations Density 0.013%

    No Known Activations