© 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. 78444
    Prev
    Next
    INDEX
    Explanations

    creating, doing, reason, ends

    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
    getElementById
    0.35
     이
    0.34
    沭
    0.33
    şi
    0.33
    ㄉ
    0.32
     向
    0.32
    querySelector
    0.32
     机
    0.32
    pdbonly
    0.32
    র্শ
    0.31
    POSITIVE LOGITS
     without
    0.51
     while
    0.43
     χωρίς
    0.42
    without
    0.40
     WITHOUT
    0.40
     Without
    0.38
    Without
    0.38
     terwijl
    0.37
     :)
    0.37
     tanpa
    0.37
    Activations Density 0.135%

    No Known Activations