© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62631
    Prev
    Next
    INDEX
    Explanations

    `read`, `write`, `file`, `range`, `if`

    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_41_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
     HEP
    0.37
     становништво
    0.37
    Sentinel
    0.36
    ట్‌లో
    0.36
    Lymph
    0.36
    ើន
    0.36
     pathetic
    0.35
    ޢ
    0.35
    gramModel
    0.34
     अमाउंट
    0.34
    POSITIVE LOGITS
    Read
    0.42
     Read
    0.42
    ಿಗೆ
    0.42
    play
    0.41
     Fill
    0.41
     Write
    0.41
    expand
    0.40
    াসা
    0.39
    parts
    0.39
    Fill
    0.39
    Activations Density 0.001%

    No Known Activations