© 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. 68395
    Prev
    Next
    INDEX
    Explanations

    discovery and unknown

    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
    予算
    0.38
     millimeter
    0.37
     kc
    0.37
    attes
    0.35
    寸
    0.35
    budget
    0.34
    LoopBlend
    0.34
    rictor
    0.34
    𝒄
    0.34
    ॅप
    0.34
    POSITIVE LOGITS
     unknown
    1.35
     discover
    1.29
     discovered
    1.29
     discovery
    1.29
     discovering
    1.26
     unknowns
    1.25
    Discover
    1.21
     Unknown
    1.20
    discovered
    1.20
     Discover
    1.19
    Activations Density 0.006%

    No Known Activations