© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223344
    Prev
    Next
    INDEX
    Explanations

    whipped up or around

    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_10_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
    ați
    0.76
    ]];
    0.71
     форм
    0.70
     proteolytic
    0.67
     موجب
    0.66
    stücke
    0.66
     протяжении
    0.65
    ه
    0.63
     آخر
    0.63
     불구하고
    0.63
    POSITIVE LOGITS
    IN
    0.72
    ının
    0.70
    I
    0.68
     Disney
    0.67
    ark
    0.65
    on
    0.64
    AR
    0.64
    Z
    0.64
     the
    0.63
     their
    0.63
    Activations Density 0.001%

    No Known Activations