© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44382
    Prev
    Next
    INDEX
    Explanations

    Reinforcement Learning

    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
    al
    0.89
     it
    0.84
     can
    0.67
    し
    0.61
    с
    0.60
    いたら
    0.59
    ിച്ച്
    0.59
    чные
    0.59
    ał
    0.59
     simile
    0.59
    POSITIVE LOGITS
    u
    0.86
    iv
    0.76
    ER
    0.72
    مو
    0.70
     infancy
    0.64
     mensuales
    0.62
    I
    0.62
    гна
    0.59
    /).
    0.58
     toz
    0.58
    Activations Density 0.002%

    No Known Activations