© 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. 139772
    Prev
    Next
    INDEX
    Explanations

    fiber optic cables

    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
    <0x0D>
    0.57
    Cute
    0.55
    Durante
    0.52
    Metal
    0.52
     de
    0.52
    Clear
    0.51
    എ
    0.51
    А
    0.49
     साथ
    0.48
    Received
    0.48
    POSITIVE LOGITS
    ar
    0.50
    cian
    0.49
    chit
    0.49
     auton
    0.49
    chn
    0.48
     Tef
    0.48
    OCITY
    0.47
    ловек
    0.47
     žmon
    0.46
     citt
    0.46
    Activations Density 0.003%

    No Known Activations