© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116012
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code constructs

    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_27_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
     プレゼント
    0.38
    稦
    0.36
     chercheurs
    0.35
    損傷
    0.35
    醀
    0.35
    クレジット
    0.35
    🥩
    0.35
     osse
    0.35
     spinors
    0.35
    颦
    0.35
    POSITIVE LOGITS
    ',
    0.38
    0.37
              
    0.37
     candidacy
    0.36
    mine
    0.36
    symbol
    0.35
     mine
    0.34
    value
    0.34
    feature
    0.34
            
    0.33
    Activations Density 0.002%

    No Known Activations