© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91206
    Prev
    Next
    INDEX
    Explanations

    may or may not

    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
    }
    0.92
    the
    0.75
    o
    0.68
    }<
    0.68
    db
    0.65
    dj
    0.64
    df
    0.64
     be
    0.63
    den
    0.63
    dal
    0.61
    POSITIVE LOGITS
    نی
    0.74
    <0x80>
    0.62
    ते
    0.61
    ிற்கு
    0.61
    шим
    0.61
    ０
    0.61
     attham
    0.61
    ви
    0.60
    रीबन
    0.60
     usuarios
    0.59
    Activations Density 0.000%

    No Known Activations