© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78638
    Prev
    Next
    INDEX
    Explanations

    are

    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_53_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
     mo
    0.42
    ි
    0.36
    ratings
    0.35
    bur
    0.35
    MUX
    0.35
    mo
    0.34
    IMM
    0.34
    imm
    0.34
     Moż
    0.34
    seleccion
    0.34
    POSITIVE LOGITS
     E
    0.99
     eş
    0.71
     ER
    0.63
     ere
    0.55
     e
    0.54
     Esh
    0.54
    Ｅ
    0.54
     Ε
    0.54
    E
    0.51
     ई
    0.50
    Activations Density 0.004%

    No Known Activations