© 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. 155312
    Prev
    Next
    INDEX
    Explanations

    Lost

    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
     deftly
    0.47
     solidly
    0.43
     mischiev
    0.42
     dreamy
    0.42
    苾
    0.42
    Tras
    0.41
     saddened
    0.41
     mischievous
    0.41
     glimmer
    0.41
    мое
    0.40
    POSITIVE LOGITS
    s
    0.70
     UW
    0.54
     carried
    0.51
    used
    0.50
     ecosystem
    0.48
    carried
    0.48
     carries
    0.44
    ی
    0.44
     control
    0.43
     council
    0.41
    Activations Density 0.002%

    No Known Activations