© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23857
    Prev
    Next
    INDEX
    Explanations

    Primary

    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_56_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
     می‌کن
    0.39
    ity
    0.39
    マンション
    0.38
    >\<^
    0.35
    夙
    0.35
    textwidth
    0.35
     racked
    0.34
    ственным
    0.34
     Lui
    0.34
    нным
    0.34
    POSITIVE LOGITS
     Primary
    0.51
    Primary
    0.48
     primary
    0.48
     PRIMARY
    0.48
     Following
    0.46
     Progressive
    0.43
    ㆍ
    0.43
     or
    0.43
    achos
    0.42
    cheid
    0.41
    Activations Density 0.002%

    No Known Activations