© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67963
    Prev
    Next
    INDEX
    Explanations

    that

    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_46_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
    Good
    0.43
     более
    0.42
     good
    0.41
     хоро
    0.40
    Very
    0.39
     Good
    0.39
     більш
    0.38
    更
    0.38
     GOOD
    0.38
    GOOD
    0.37
    POSITIVE LOGITS
     सबसे
    1.95
    最
    1.84
     가장
    1.80
     সবচেয়ে
    1.73
     nhất
    1.71
    सबसे
    1.70
     સૌથી
    1.70
     greatest
    1.68
     fastest
    1.68
     най
    1.68
    Activations Density 0.011%

    No Known Activations