© 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. 216738
    Prev
    Next
    INDEX
    Explanations

    English language identifiers

    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
    ᆯ
    0.43
    elson
    0.41
    jl
    0.40
    ला
    0.40
    eil
    0.40
    etli
    0.40
     posX
    0.40
    іл
    0.40
    डल
    0.40
    lighet
    0.39
    POSITIVE LOGITS
    毂
    0.41
    ຶ
    0.38
     Blink
    0.38
     Hurd
    0.37
    க்கண
    0.36
     يطلع
    0.36
     transcribed
    0.35
     CV
    0.35
    ienst
    0.35
    풍
    0.34
    Activations Density 0.000%

    No Known Activations