© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20667
    Prev
    Next
    INDEX
    Explanations

    ,

    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_56_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
     v
    0.48
     amusing
    0.44
     menacing
    0.44
     slightly
    0.44
     frustrating
    0.42
     intimidating
    0.42
     terrifying
    0.42
     frightening
    0.42
     V
    0.41
     Judging
    0.41
    POSITIVE LOGITS
     willingness
    0.70
     willing
    0.69
    willing
    0.64
     Willing
    0.53
    願意
    0.48
     w
    0.44
    愿意
    0.44
     gratitude
    0.43
     mut
    0.43
     extending
    0.42
    Activations Density 0.033%

    No Known Activations