© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142081
    Prev
    Next
    INDEX
    Explanations

    doping

    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_0_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
    ன்
    1.42
    ন
    1.42
    ని
    1.41
    ل
    1.41
    з
    1.40
    л
    1.34
    ن
    1.32
    ব
    1.31
    <0xBB>
    1.30
    {
    1.30
    POSITIVE LOGITS
    p
    1.13
     लड़ा
    1.10
    </h2>
    1.07
    we
    1.05
    ע
    1.05
     l
    1.03
    ING
    1.02
    c
    1.02
     you
    0.99
    大
    0.99
    Activations Density 0.000%

    No Known Activations