© 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. 49777
    Prev
    Next
    INDEX
    Explanations

    Super

    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
     rbind
    0.44
     du
    0.39
     indoctr
    0.38
    ⑰
    0.38
     Du
    0.38
     Су
    0.35
    ębior
    0.35
    ʕ
    0.35
     odm
    0.35
    BigAutoField
    0.35
    POSITIVE LOGITS
     super
    0.66
    super
    0.59
    超
    0.55
    very
    0.52
     siêu
    0.52
    core
    0.49
     супер
    0.49
    multiple
    0.48
    非常に
    0.47
    vor
    0.46
    Activations Density 0.003%

    No Known Activations