© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45355
    Prev
    Next
    INDEX
    Explanations

    image URLs with /thumb/

    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_22_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
     attractions
    0.42
     TextAlign
    0.41
     cardiomyocytes
    0.40
    সঙ্গত
    0.40
     playerCount
    0.39
    冲
    0.38
     hMut
    0.38
     tecnici
    0.38
     begonnen
    0.38
    逞
    0.38
    POSITIVE LOGITS
    ABS
    0.47
    lens
    0.46
     в
    0.44
    neat
    0.43
     سف
    0.41
     ABS
    0.41
    embed
    0.40
    quad
    0.40
    Nguyen
    0.40
    送
    0.39
    Activations Density 0.000%

    No Known Activations