© 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. 16977
    Prev
    Next
    INDEX
    Explanations

    diagrams, code, or text structure

    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
     ---
    1.95
    ---
    1.71
     ----
    1.64
     ——
    1.63
     —,
    1.63
     -----
    1.59
    ----
    1.53
    —.
    1.53
    -----
    1.52
     ------
    1.50
    POSITIVE LOGITS
    緹
    0.45
    謖
    0.40
    RICT
    0.38
    ĥ
    0.36
    缇
    0.36
    etri
    0.36
    DEC
    0.36
    လဲ
    0.35
    सत्ता
    0.34
     جري
    0.34
    Activations Density 0.035%

    No Known Activations