© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124086
    Prev
    Next
    INDEX
    Explanations

    seward, seolnal, copywriter

    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_3_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
     you
    0.76
    0
    0.75
    ]);
    0.73
     to
    0.71
     нём
    0.68
     decidió
    0.66
    میر
    0.65
     that
    0.64
     cataly
    0.63
    คุณ
    0.63
    POSITIVE LOGITS
    ان
    0.89
    a
    0.89
    an
    0.82
    et
    0.69
    am
    0.67
    ᅢ
    0.66
    么
    0.63
    es
    0.63
    h
    0.63
    e
    0.62
    Activations Density 0.001%

    No Known Activations