© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175638
    Prev
    Next
    INDEX
    Explanations

    historical and technical terms

    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_20_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
     कैद
    0.38
     टेस्टिंग
    0.38
     Postgres
    0.38
     теория
    0.37
    ⏟
    0.37
     Duty
    0.37
     कैंपस
    0.37
     Казино
    0.36
     captivity
    0.36
    烬
    0.36
    POSITIVE LOGITS
    left
    0.39
    was
    0.38
     was
    0.36
    當時
    0.36
    irati
    0.35
    iran
    0.35
     LEFT
    0.33
     scatter
    0.33
    irat
    0.33
     salah
    0.32
    Activations Density 0.016%

    No Known Activations