© 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. 200767
    Prev
    Next
    INDEX
    Explanations

    requests

    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
     mapView
    0.41
     К
    0.40
    itali
    0.40
     K
    0.39
     कोलकाता
    0.39
    masını
    0.39
    মা
    0.38
     Kran
    0.38
     Medik
    0.38
     ক্রো
    0.38
    POSITIVE LOGITS
     An
    0.63
    An
    0.56
     AN
    0.54
    AN
    0.44
     AG
    0.44
    <0x8E>
    0.44
     sahi
    0.42
    安
    0.41
     AGS
    0.40
     Anh
    0.39
    Activations Density 0.002%

    No Known Activations