© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150768
    Prev
    Next
    INDEX
    Explanations

    check

    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_60_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
    </i>
    0.40
    лка
    0.39
    K
    0.38
    M
    0.38
    ↵↵
    0.37
    LES
    0.37
     сум
    0.37
    п
    0.36
    PRA
    0.36
     wv
    0.35
    POSITIVE LOGITS
    haber
    0.45
    for
    0.44
    produkte
    0.43
     produkter
    0.43
    haft
    0.42
    isos
    0.42
    artig
    0.41
    rä
    0.41
    are
    0.40
    hej
    0.40
    Activations Density 0.000%

    No Known Activations