© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50605
    Prev
    Next
    INDEX
    Explanations

    Polish

    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_55_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
    щ
    0.36
     precipitates
    0.36
    igos
    0.34
     успо
    0.34
     করিলে
    0.33
    తం
    0.33
     earum
    0.33
     searchObject
    0.33
    翻
    0.33
     ullam
    0.32
    POSITIVE LOGITS
     lod
    0.53
     Lod
    0.52
    Lod
    0.50
    lod
    0.42
     zn
    0.40
     lodging
    0.40
     lodged
    0.37
     let
    0.36
     dor
    0.36
    Gro
    0.36
    Activations Density 0.001%

    No Known Activations