© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54564
    Prev
    Next
    INDEX
    Explanations

    Over

    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_55_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
     overcome
    0.57
     преодо
    0.50
    克服
    0.48
     overcomes
    0.47
    break
    0.46
    рыва
    0.41
    唑
    0.41
     overcoming
    0.40
    breaks
    0.39
    Exit
    0.39
    POSITIVE LOGITS
     активно
    0.41
     winning
    0.40
     actively
    0.40
     اعت
    0.39
     лю
    0.39
     ресур
    0.38
    毋
    0.38
    potent
    0.38
     Winning
    0.38
     appren
    0.38
    Activations Density 0.001%

    No Known Activations