© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237616
    Prev
    Next
    INDEX
    Explanations

    the way [person] [does something]

    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_32_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
     blu
    0.34
     Lionel
    0.33
     வேளா
    0.33
    Lionel
    0.33
     Euse
    0.33
    utional
    0.32
     তোমার
    0.32
    ()-
    0.32
    WY
    0.32
    enste
    0.32
    POSITIVE LOGITS
    解答
    0.36
    SError
    0.36
     चै
    0.33
    Passive
    0.32
    మారు
    0.32
    髓
    0.32
    ahmatullahi
    0.32
    也可
    0.31
    izophren
    0.31
     recklessly
    0.31
    Activations Density 0.003%

    No Known Activations