© 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. 45112
    Prev
    Next
    INDEX
    Explanations

    Q-learning and efficiency

    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
    .,
    0.81
    ე
    0.71
    I
    0.69
    Z
    0.66
    ğ
    0.66
    ж
    0.64
    াস
    0.63
    EP
    0.62
    logs
    0.62
    gn
    0.61
    POSITIVE LOGITS
    ről
    0.76
    ról
    0.61
     is
    0.60
    ampuan
    0.57
    و
    0.57
    يا
    0.57
     symbiotic
    0.57
     découvert
    0.55
     snowboard
    0.55
     totalité
    0.55
    Activations Density 0.006%

    No Known Activations