© 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. 194685
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ചെറു
    0.42
    TakePhoto
    0.39
    सुम
    0.39
    ため
    0.38
    िसो
    0.38
    ำ
    0.38
     деко
    0.37
    するため
    0.37
    Section
    0.37
    ₲
    0.36
    POSITIVE LOGITS
     bart
    0.38
     logement
    0.35
     urt
    0.34
     effected
    0.34
     instance
    0.33
     hiszen
    0.33
     seis
    0.33
     бывает
    0.33
     geval
    0.32
     hilfre
    0.32
    Activations Density 0.000%

    No Known Activations