© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236780
    Prev
    Next
    INDEX
    Explanations

    URL parameters

    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_46_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
    itaires
    0.45
    LOCATION
    0.43
    Location
    0.39
    estr
    0.38
    миз
    0.38
    γα
    0.38
    ዎት
    0.37
    댄
    0.37
    browse
    0.37
    不到
    0.37
    POSITIVE LOGITS
     Vara
    0.42
    rong
    0.41
     Markle
    0.38
    િયલ
    0.38
     Mash
    0.37
    喈
    0.37
     Mard
    0.36
     Massey
    0.35
     CaCl
    0.35
     Bak
    0.34
    Activations Density 0.000%

    No Known Activations