© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133329
    Prev
    Next
    INDEX
    Explanations

    describing places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ba
    0.45
     flutter
    0.40
    am
    0.38
    ㄺ
    0.38
     አማ
    0.37
     Flutter
    0.37
    食べて
    0.37
     Bailey
    0.37
    atasi
    0.37
     thất
    0.37
    POSITIVE LOGITS
     클
    0.70
    Cl
    0.65
    cl
    0.64
     Cl
    0.61
     kl
    0.60
     cl
    0.59
     کل
    0.58
    کل
    0.56
     क्ल
    0.56
     Kl
    0.55
    Activations Density 0.000%

    No Known Activations