© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31427
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by content

    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_40_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
     jl
    0.47
     vorm
    0.40
    υχ
    0.39
    腈
    0.39
     vsize
    0.38
    Packages
    0.38
    Klein
    0.38
     qty
    0.37
    ্ধ্য
    0.37
    ڱ
    0.37
    POSITIVE LOGITS
     Rapids
    0.40
     Safari
    0.39
     intents
    0.39
    buff
    0.39
     Expl
    0.38
     Stay
    0.37
     ड्र
    0.36
    Rationale
    0.36
     Buffet
    0.35
     Purpose
    0.35
    Activations Density 0.018%

    No Known Activations