© 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. 206332
    Prev
    Next
    INDEX
    Explanations

    discovery

    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
     kc
    0.39
     millimeter
    0.38
     പ്രതിഷേധ
    0.36
    ابه
    0.36
    𝒄
    0.34
     commissioner
    0.34
     איז
    0.34
    rictor
    0.34
    𝘳
    0.34
    上限
    0.34
    POSITIVE LOGITS
     unknown
    1.41
     discovery
    1.37
     discover
    1.36
     discovered
    1.36
     discovering
    1.35
     unknowns
    1.31
    discover
    1.26
    discovered
    1.26
    Discover
    1.24
     Discover
    1.23
    Activations Density 0.037%

    No Known Activations