© 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. 176144
    Prev
    Next
    INDEX
    Explanations

    handles complexities for you

    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
     flanges
    0.35
    க்கர
    0.34
     visions
    0.34
     antics
    0.34
    越南
    0.33
     Leo
    0.33
     orifices
    0.32
    씽
    0.32
     outbursts
    0.31
    ؤول
    0.31
    POSITIVE LOGITS
    cached
    0.34
     കൃ
    0.34
    essä
    0.33
    qués
    0.33
     ที่
    0.33
    dried
    0.32
    otoxin
    0.32
     ഗവേഷ
    0.31
    urium
    0.31
     മാര്‍
    0.31
    Activations Density 0.003%

    No Known Activations