© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102065
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    ℕ
    0.42
    cinas
    0.39
    λια
    0.38
    ieck
    0.37
     Ex
    0.37
    medieval
    0.36
    anym
    0.36
    ᆨ
    0.36
    writeInt
    0.36
     ex
    0.36
    POSITIVE LOGITS
     प्रशंसा
    0.41
    afir
    0.38
    ຮັບ
    0.38
     Carlisle
    0.38
    င်
    0.37
    Penumpang
    0.37
    עם
    0.36
    收
    0.36
     Phillips
    0.36
     laga
    0.35
    Activations Density 0.000%

    No Known Activations