© 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. 92308
    Prev
    Next
    INDEX
    Explanations

    le

    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
    m
    0.74
    nis
    0.66
    nin
    0.64
    ni
    0.63
    nen
    0.62
    nym
    0.62
    nem
    0.61
    f
    0.60
    nas
    0.60
    nes
    0.59
    POSITIVE LOGITS
    Cr
    0.77
     Cr
    0.71
     le
    0.69
    cr
    0.65
     cr
    0.57
    ت
    0.48
     crackers
    0.44
    ans
    0.44
     copies
    0.40
     ле
    0.39
    Activations Density 0.000%

    No Known Activations