© 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. 164673
    Prev
    Next
    INDEX
    Explanations

    lists within code blocks

    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
     Trock
    0.49
     liberté
    0.49
    たとえば
    0.47
    ствий
    0.46
    ిన
    0.46
     capelli
    0.45
     т
    0.44
    瓈
    0.44
     نە
    0.43
     Dyson
    0.43
    POSITIVE LOGITS
    /
    0.68
    ura
    0.60
    ni
    0.59
    ur
    0.57
    ank
    0.57
    uv
    0.56
    om
    0.56
    red
    0.56
    amin
    0.56
    )
    0.55
    Activations Density 0.001%

    No Known Activations