© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33839
    Prev
    Next
    INDEX
    Explanations

    I want to VERB

    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_7_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
    ل
    0.71
    un
    0.59
    ↵
    0.58
    ul
    0.56
    in
    0.55
    an
    0.55
    ar
    0.54
    ur
    0.52
    le
    0.50
    ن
    0.49
    POSITIVE LOGITS
    ،
    0.54
    »:
    0.53
    >:
    0.52
    ^{-}
    0.52
    gebaut
    0.49
    ^{*}
    0.49
     δύο
    0.48
     four
    0.47
     冖
    0.46
    ᄑ
    0.46
    Activations Density 0.019%

    No Known Activations