© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46736
    Prev
    Next
    INDEX
    Explanations

    drops, aid, or throw away

    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_13_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
     e
    0.52
    _);
    0.51
     metros
    0.50
     अन्य
    0.49
     McLaughlin
    0.48
     otros
    0.47
     दूसरे
    0.47
    ورش
    0.47
    <0x83>
    0.46
     other
    0.46
    POSITIVE LOGITS
     జరిగింది
    0.54
     подар
    0.51
    rewards
    0.51
    🎁
    0.50
    at
    0.48
    抛
    0.47
    gift
    0.46
    Rewards
    0.45
    filament
    0.45
     Rewards
    0.44
    Activations Density 0.059%

    No Known Activations