© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233250
    Prev
    Next
    INDEX
    Explanations

    say ".\ "

    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
    ClientId
    0.40
    拝
    0.39
     carcin
    0.37
     CNC
    0.37
    станти
    0.36
    ＠
    0.36
    ClientID
    0.36
    ヱ
    0.36
     tangled
    0.36
     harms
    0.35
    POSITIVE LOGITS
    偏移
    0.37
     cw
    0.37
    𝑅
    0.37
     R
    0.36
     [
    0.36
     cb
    0.35
    cw
    0.35
     Rotate
    0.35
    marquee
    0.35
     Rc
    0.35
    Activations Density 0.003%

    No Known Activations