© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12448
    Prev
    Next
    INDEX
    Explanations

    drawing and frameworks

    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_13_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
    ovin
    0.46
    est
    0.45
    oS
    0.45
    aw
    0.45
    ot
    0.45
    hat
    0.45
     ד
    0.44
    osit
    0.44
    ']).
    0.44
    ord
    0.43
    POSITIVE LOGITS
    钲
    0.50
    संगिक
    0.47
     paisaje
    0.46
     передба
    0.45
     foresee
    0.45
     parku
    0.44
     mensen
    0.42
     condemn
    0.42
     kerül
    0.42
     Vào
    0.42
    Activations Density 0.051%

    No Known Activations