© 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. 123307
    Prev
    Next
    INDEX
    Explanations

    TFLOPS

    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
    s
    0.90
    y
    0.75
    ים
    0.71
     درسنا
    0.69
    ς
    0.66
    siniz
    0.66
    વવા
    0.65
    れの
    0.65
    ри
    0.64
    વતી
    0.64
    POSITIVE LOGITS
     in
    0.79
     is
    0.74
    _
    0.72
    ك
    0.71
    at
    0.70
    and
    0.70
    К
    0.70
    }=\
    0.65
    ose
    0.65
    ese
    0.64
    Activations Density 0.001%

    No Known Activations