© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61398
    Prev
    Next
    INDEX
    Explanations

    for

    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_59_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
     sake
    0.64
     to
    0.50
    illa
    0.41
     The
    0.40
    ಂತ್ರ
    0.38
    inate
    0.37
    Whatever
    0.37
    ᱒
    0.37
    ප
    0.37
    to
    0.37
    POSITIVE LOGITS
    Reasons
    0.63
     reasons
    0.62
     Reasons
    0.61
     mainly
    0.48
    理由は
    0.47
     mostly
    0.46
     Gründe
    0.46
     principalement
    0.46
     Mostly
    0.44
    理由
    0.44
    Activations Density 0.009%

    No Known Activations