© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241780
    Prev
    Next
    INDEX
    Explanations

    .value

    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_40_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
     value
    0.47
    value
    0.47
    Entering
    0.43
    enter
    0.42
    label
    0.41
    Enter
    0.40
    値
    0.40
     κατο
    0.40
    后
    0.40
     enter
    0.39
    POSITIVE LOGITS
     বাড়
    0.41
     Pb
    0.38
    ibley
    0.38
     संजीव
    0.37
     প্রতিযোগ
    0.36
     Sous
    0.35
     Теннис
    0.35
     объявления
    0.35
     ضرب
    0.35
     конкурс
    0.35
    Activations Density 0.000%

    No Known Activations