© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204815
    Prev
    Next
    INDEX
    Explanations

    stock vs default/original

    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_6_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
    ン
    0.98
    н
    0.91
    ת
    0.84
    си
    0.78
    Т
    0.76
    ारा
    0.76
    uenza
    0.70
     andRow
    0.70
    𝗙
    0.70
    lated
    0.69
    POSITIVE LOGITS
    é
    0.82
     were
    0.82
    ec
    0.81
    e
    0.80
    os
    0.80
     siendo
    0.77
    ின்
    0.75
     levant
    0.75
    o
    0.75
     zijn
    0.75
    Activations Density 0.000%

    No Known Activations