© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14896
    Prev
    Next
    INDEX
    Explanations

    KEY AUTOINCREMENT

    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_40_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
    Gandhi
    0.45
     čet
    0.43
    芰
    0.43
     கழி
    0.41
     درجه
    0.40
    Bible
    0.40
     আধ
    0.40
     çeşit
    0.40
    幅
    0.39
    Gaz
    0.38
    POSITIVE LOGITS
     tobacco
    0.41
     Tobacco
    0.38
    Tomas
    0.38
     Tomas
    0.37
    **.
    0.37
     tob
    0.36
     streamlit
    0.36
    เร็ว
    0.36
    tob
    0.36
     Tob
    0.35
    Activations Density 0.012%

    No Known Activations