© 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. 52467
    Prev
    Next
    INDEX
    Explanations

    chooses a road

    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
     wybr
    0.43
     meteen
    0.40
     निवड
    0.38
    ργαν
    0.38
    indon
    0.37
     rapor
    0.37
     mostrou
    0.37
    选
    0.36
    褰
    0.36
     afront
    0.36
    POSITIVE LOGITS
     ช
    0.35
    嘚
    0.32
     ​​
    0.32
     ${
    0.31
     sedentary
    0.31
     মিঠ
    0.31
     Click
    0.31
     Case
    0.31
     հատ
    0.31
     supplementation
    0.30
    Activations Density 0.023%

    No Known Activations