© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58297
    Prev
    Next
    INDEX
    Explanations

    a

    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_59_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
     [&
    0.43
    ).
    0.40
    zus
    0.40
    zten
    0.40
    $)$.
    0.40
     নৈতিক
    0.39
    );
    0.38
    )+
    0.37
    </li>
    0.37
    )&
    0.37
    POSITIVE LOGITS
    –
    0.43
    Κ
    0.42
    」（
    0.41
    produkt
    0.40
    clave
    0.40
    TO
    0.40
    snow
    0.39
    ‑
    0.38
    ﾊ
    0.38
    
    0.38
    Activations Density 0.002%

    No Known Activations