© 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. 81765
    Prev
    Next
    INDEX
    Explanations

    mit

    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
    impero
    0.39
    号
    0.39
    ミ
    0.37
    原来的
    0.36
    viso
    0.35
    미
    0.35
    明治
    0.34
    methylation
    0.34
     ш
    0.34
    дь
    0.34
    POSITIVE LOGITS
    chel
    0.51
    hel
    0.50
    chelle
    0.49
    cha
    0.48
    heli
    0.46
    hael
    0.45
    HEL
    0.44
    CHE
    0.44
    CELL
    0.44
     Chel
    0.44
    Activations Density 0.002%

    No Known Activations