© 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. 2220
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_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
    <0xB3>
    0.55
    7
    0.49
     bảy
    0.49
     ७
    0.48
     ۷
    0.48
    ７
    0.47
    𝟕
    0.46
     seven
    0.46
     ৭
    0.46
    ७
    0.43
    POSITIVE LOGITS
     девя
    0.45
    九
    0.42
    ৪২
    0.41
    4
    0.38
    LoginID
    0.38
     Nine
    0.37
    Nin
    0.37
    CIO
    0.36
    Forty
    0.36
     consignment
    0.36
    Activations Density 0.040%

    No Known Activations