© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108113
    Prev
    Next
    INDEX
    Explanations

    code delimiters and characters

    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_1_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
             
    0.99
    ルの
    0.95
    Я
    0.95
     gră
    0.93
          
    0.92
                            
    0.91
     referendum
    0.91
     segreg
    0.91
     robbery
    0.91
     microfilm
    0.91
    POSITIVE LOGITS
    s
    1.74
     a
    1.22
    ים
    1.17
    ς
    1.16
    ור
    1.12
    ्स
    1.09
    स
    1.09
    že
    1.07
    ية
    1.06
    ો
    1.05
    Activations Density 0.000%

    No Known Activations