© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34839
    Prev
    Next
    INDEX
    Explanations

    explanations of why or when

    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_31_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
     proie
    0.39
     koş
    0.37
    घ
    0.37
     displace
    0.36
    Elle
    0.35
    )(=
    0.35
     diperlukan
    0.34
     Bereiche
    0.34
     balans
    0.34
    ​​
    0.34
    POSITIVE LOGITS
     detectives
    0.42
     শেষের
    0.40
     griseo
    0.40
     babies
    0.39
     हत्याकांड
    0.39
     ആഘോഷ
    0.38
     வாழ்வில்
    0.38
     キッズ
    0.38
     детям
    0.37
    澍
    0.37
    Activations Density 0.015%

    No Known Activations