© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14278
    Prev
    Next
    INDEX
    Explanations

    Kubrick, Telegraph Avenue

    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_15_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
     गोल्ड
    0.12
    CallBack
    0.11
    ρ
    0.10
     गर्मियों
    0.10
     Louisiana
    0.10
     Questions
    0.10
    がお
    0.10
    RequestParam
    0.10
    Callbacks
    0.10
     समस्याओं
    0.10
    POSITIVE LOGITS
     be
    0.11
     deceive
    0.11
     trialComponents
    0.11
    zinha
    0.11
     и
    0.11
     tinc
    0.10
    astien
    0.10
     couldn
    0.10
     läbi
    0.10
     və
    0.10
    Activations Density 0.003%

    No Known Activations