© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78875
    Prev
    Next
    INDEX
    Explanations

    visual concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    uksen
    1.32
    }$;
    1.16
    kiego
    1.11
    行う
    1.07
     públicas
    1.03
     dovoljno
    1.02
     buoni
    1.02
    ่า
    1.01
    の問題
    1.01
    の話
    1.01
    POSITIVE LOGITS
    t
    2.27
    the
    1.90
    s
    1.65
    c
    1.56
    ند
    1.54
    ش
    1.42
    p
    1.36
    sl
    1.34
    بت
    1.34
    ें
    1.33
    Activations Density 0.005%

    No Known Activations