© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206382
    Prev
    Next
    INDEX
    Explanations

    less than comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    不超过
    0.54
    筏
    0.46
     Limits
    0.43
    ğraf
    0.43
     Fär
    0.41
    ημ
    0.41
    ਨੇ
    0.40
    ۇ
    0.39
    નિક
    0.39
     фильма
    0.38
    POSITIVE LOGITS
     hazard
    0.49
    hazard
    0.48
     minimum
    0.45
     shopping
    0.45
     minima
    0.44
    евич
    0.44
     synov
    0.44
     ---------
    0.44
    min
    0.42
     operating
    0.42
    Activations Density 0.009%

    No Known Activations