© 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. 150703
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     et
    0.48
    、
    0.42
     چیمپ
    0.40
    ‌,
    0.39
    ፣
    0.39
    在线
    0.38
    TextMessage
    0.37
     பேரும்
    0.37
    就是一个
    0.37
    %；
    0.37
    POSITIVE LOGITS
     e
    0.40
    Needless
    0.40
     ຈ
    0.39
     );
    0.38
     Generally
    0.38
    </h6>
    0.36
    generally
    0.36
     [...]
    0.36
    ',)
    0.35
     Similarly
    0.34
    Activations Density 0.001%

    No Known Activations