© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151068
    Prev
    Next
    INDEX
    Explanations

    to

    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
     c
    0.60
     Help
    0.52
     help
    0.47
     grant
    0.46
     Give
    0.44
     Grant
    0.43
     Fight
    0.43
     ص
    0.42
    𝘤
    0.42
    Help
    0.42
    POSITIVE LOGITS
     crack
    0.71
     flag
    0.60
    crack
    0.59
    flag
    0.57
    Crack
    0.54
     log
    0.51
     FLAG
    0.49
    Flag
    0.49
    log
    0.48
     Crack
    0.47
    Activations Density 0.004%

    No Known Activations