© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207168
    Prev
    Next
    INDEX
    Explanations

    time

    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
     ك
    0.44
     consommation
    0.44
     스트
    0.42
     caes
    0.41
    加えて
    0.40
    만
    0.39
     ferr
    0.38
     taille
    0.38
     великолеп
    0.38
     feria
    0.38
    POSITIVE LOGITS
    
    0.43
    ωσης
    0.42
    טים
    0.41
    atsii
    0.41
    DBES
    0.41
    льного
    0.40
    oclonal
    0.40
     ,'
    0.40
     Assad
    0.40
     Балт
    0.40
    Activations Density 0.003%

    No Known Activations