© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13342
    Prev
    Next
    INDEX
    Explanations

    union all

    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_13_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
    کریاں
    0.13
    遊び
    0.12
    ポーツ
    0.12
     headlight
    0.12
     ಎಂಬುದ
    0.12
    ၡ
    0.12
    <unused44>
    0.12
    netfx
    0.11
     humains
    0.11
    >∞</
    0.11
    POSITIVE LOGITS
    ו
    0.16
    in
    0.13
      
    0.13
     tentar
    0.13
    ↵↵↵↵
    0.12
     Case
    0.12
     may
    0.12
     PPI
    0.12
                
    0.12
    inni
    0.12
    Activations Density 0.009%

    No Known Activations