© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205688
    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_37_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
     keine
    0.41
    沭
    0.40
     funktion
    0.38
     الفرنسي
    0.38
    urik
    0.38
     koff
    0.38
     French
    0.37
    ž
    0.37
     faible
    0.36
     최고
    0.36
    POSITIVE LOGITS
     creencias
    0.41
     degrad
    0.40
     degradation
    0.37
    COVER
    0.37
     connectedness
    0.37
    Bonnie
    0.36
     biodegradation
    0.35
    ())).
    0.35
    Pand
    0.35
    Adjacent
    0.35
    Activations Density 0.000%

    No Known Activations