© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127483
    Prev
    Next
    INDEX
    Explanations

    other reasons

    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_3_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
    у
    1.06
    е
    0.84
    ดี
    0.70
    ко
    0.66
    '
    0.65
    то
    0.64
    తి
    0.63
    ที่
    0.61
    ation
    0.61
     inconsider
    0.60
    POSITIVE LOGITS
    0
    0.78
    orov
    0.71
     Gewicht
    0.65
    রামর্শ
    0.64
    woch
    0.64
    Yea
    0.64
    fie
    0.63
    José
    0.63
    ydd
    0.63
    franch
    0.62
    Activations Density 0.001%

    No Known Activations