© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 2535
    Prev
    Next
    INDEX
    Explanations

    legal precedents

    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_38_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
    Воз
    0.37
    碖
    0.36
    ihn
    0.35
    Sd
    0.35
     analogies
    0.35
    /');
    0.34
    หมือน
    0.34
    getItemId
    0.34
    Anyways
    0.34
    वेदन
    0.33
    POSITIVE LOGITS
     precept
    0.47
     Bad
    0.45
     privind
    0.44
    壞
    0.44
    坏
    0.43
     GCC
    0.42
     bad
    0.40
    BAD
    0.40
     marshal
    0.40
     BAD
    0.40
    Activations Density 0.095%

    No Known Activations