© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 36729
    Prev
    Next
    INDEX
    Explanations

    names like Kennedy, Swan, Aber, Lee, Dante

    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
    ໃຊ
    0.69
    a
    0.66
    y
    0.63
    yczne
    0.62
    هی
    0.61
    cando
    0.61
    ा
    0.61
    া
    0.61
    ка
    0.61
    rangea
    0.59
    POSITIVE LOGITS
    0.92
    ى
    0.76
     RECOMM
    0.55
    !\
    0.54
     BURN
    0.53
     powied
    0.52
    Ul
    0.52
     dingen
    0.52
     WITH
    0.51
     }}
    0.50
    Activations Density 0.001%

    No Known Activations