© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166006
    Prev
    Next
    INDEX
    Explanations

    side effects

    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_31_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
     пользователи
    0.38
     εξα
    0.37
     użytk
    0.37
     agrad
    0.37
     svě
    0.36
     யா
    0.36
     用户
    0.35
    缪
    0.35
     gebra
    0.34
     rég
    0.34
    POSITIVE LOGITS
    Raising
    0.38
    ometh
    0.37
     anti
    0.36
    orse
    0.36
     proceed
    0.34
     proceeds
    0.34
     wild
    0.34
     proceeded
    0.33
     hare
    0.33
    殲
    0.33
    Activations Density 0.006%

    No Known Activations