© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9984
    Prev
    Next
    INDEX
    Explanations

    pull request

    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_13_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
    原则
    0.54
    a
    0.52
    iet
    0.49
     některé
    0.48
    0.47
    id
    0.46
    0.45
    Connect
    0.45
     principle
    0.44
     tract
    0.44
    POSITIVE LOGITS
     cH
    0.57
     `'\\
    0.55
     производ
    0.55
     Offered
    0.54
     Pressed
    0.53
     Obviously
    0.52
     Gm
    0.52
    amesh
    0.51
    𝚢
    0.51
     Hours
    0.51
    Activations Density 0.014%

    No Known Activations