© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38735
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    Ent
    0.43
     Ent
    0.43
    Grunt
    0.38
    偃
    0.38
     Dam
    0.37
     надо
    0.37
    Mad
    0.36
    Pad
    0.36
     Gr
    0.35
     Cr
    0.35
    POSITIVE LOGITS
     childrens
    0.47
     polarity
    0.39
     lapse
    0.38
     soldi
    0.38
     छोटे
    0.38
     effective
    0.37
    وزی
    0.36
    體
    0.36
     children
    0.35
     seascape
    0.35
    Activations Density 0.004%

    No Known Activations