© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174896
    Prev
    Next
    INDEX
    Explanations

    opportunity or chance

    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
    
    0.34
     Pierce
    0.33
     fühlen
    0.32
     FEEL
    0.32
     Pearce
    0.32
     Peirce
    0.32
     سرح
    0.31
    にする
    0.31
     plutôt
    0.31
     Dorn
    0.31
    POSITIVE LOGITS
    Equipment
    0.34
    ΟΣ
    0.33
    성
    0.33
    フロー
    0.32
    DER
    0.31
    ోంది
    0.30
    Fra
    0.30
    Grupo
    0.30
     químicos
    0.30
    액
    0.30
    Activations Density 0.001%

    No Known Activations