© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199479
    Prev
    Next
    INDEX
    Explanations

    Il existe

    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_27_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
     dell
    0.43
     everything
    0.40
    ↵↵
    0.40
     ху
    0.40
     Dell
    0.40
     ·
    0.39
     (
    0.38
     Н
    0.38
     NOT
    0.38
     хрони
    0.38
    POSITIVE LOGITS
    Longueur
    0.55
    iftoire
    0.55
     moteurs
    0.51
     restent
    0.50
     mécanisme
    0.50
    Comme
    0.48
    moins
    0.47
     fermé
    0.47
     médicament
    0.47
     rô
    0.46
    Activations Density 0.001%

    No Known Activations