© 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. 200193
    Prev
    Next
    INDEX
    Explanations

    biological family

    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
     fidelity
    0.43
    ostrat
    0.38
    fidelity
    0.38
     Separation
    0.37
    Aub
    0.37
     Fid
    0.37
    ündet
    0.36
    仕
    0.36
     lunghezza
    0.35
     складі
    0.35
    POSITIVE LOGITS
     centers
    0.37
     superfamily
    0.36
    μμ
    0.34
    immel
    0.34
    àng
    0.33
     synd
    0.33
     family
    0.33
    家族
    0.32
     lanjut
    0.32
     Cách
    0.32
    Activations Density 0.001%

    No Known Activations