© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134964
    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_6_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
    もら
    0.89
     conflicting
    0.83
     \
    0.82
     neighboring
    0.80
     compounded
    0.80
     شہریوں
    0.80
     barrios
    0.79
     personas
    0.78
     ancora
    0.77
     הב
    0.77
    POSITIVE LOGITS
    is
    1.18
    يي
    1.06
    ة
    1.06
    A
    1.04
    O
    1.03
    ă
    1.02
    F
    1.00
    తో
    0.99
    первых
    0.99
    al
    0.98
    Activations Density 0.000%

    No Known Activations