© 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. 38944
    Prev
    Next
    INDEX
    Explanations

    positioned to

    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
    downs
    0.69
     orgánica
    0.64
    ст
    0.62
    т
    0.62
    त
    0.61
    <0xBB>
    0.56
    ည့်
    0.56
    cón
    0.55
    K
    0.54
     IQR
    0.53
    POSITIVE LOGITS
     to
    0.95
    ado
    0.84
    </h2>
    0.81
    0
    0.74
    的两
    0.71
    </em>
    0.70
    <0x0D>
    0.69
    </u>
    0.68
    ADO
    0.66
    1
    0.63
    Activations Density 0.017%

    No Known Activations