© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130738
    Prev
    Next
    INDEX
    Explanations

    Dam followed by -nation, -ian, -aged, or names like Damian, Damiano, Damaya

    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
     or
    0.98
     Essentials
    0.89
    '
    0.89
     Arts
    0.88
    ’
    0.85
    ک
    0.84
     What
    0.83
     Our
    0.81
    र
    0.79
     Out
    0.77
    POSITIVE LOGITS
    s
    1.15
    on
    1.00
    㶲
    0.82
    もら
    0.80
    alım
    0.79
    ের
    0.79
    oną
    0.79
    e
    0.78
    も
    0.77
    ıdır
    0.75
    Activations Density 0.001%

    No Known Activations