© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138159
    Prev
    Next
    INDEX
    Explanations

    .ai domains or .community names

    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_12_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
    рыя
    0.51
    Autoresizing
    0.50
    dés
    0.49
    ovce
    0.48
    ᅮ
    0.48
     preclude
    0.47
    lL
    0.47
    lessly
    0.46
    AutoSize
    0.46
     peraturan
    0.46
    POSITIVE LOGITS
    ų
    0.64
    ંત
    0.60
     to
    0.59
    К
    0.57
     FRANK
    0.56
     compassion
    0.55
     CHAR
    0.54
     Бе
    0.53
    Бе
    0.53
     Вол
    0.52
    Activations Density 0.000%

    No Known Activations