© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165525
    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_31_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
     किस्त
    0.35
    OHN
    0.35
     다니
    0.34
    前
    0.33
     precedes
    0.33
    iggle
    0.33
    tiin
    0.33
    ijd
    0.32
     যাহ
    0.32
     homomorphism
    0.32
    POSITIVE LOGITS
     परिभाषित
    0.41
    വൈ
    0.41
     fuentes
    0.41
    ভিত্তিক
    0.40
     fehér
    0.40
     Climate
    0.39
    =”
    0.39
     необходимости
    0.38
     defined
    0.38
     fuente
    0.38
    Activations Density 0.000%

    No Known Activations