© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45513
    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_13_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
     Clothes
    0.48
    賚
    0.48
    ర్కొ
    0.46
    愍
    0.46
     كرة
    0.46
    促
    0.46
     Violence
    0.45
     لكرة
    0.45
    巉
    0.45
    冲突
    0.44
    POSITIVE LOGITS
    ad
    0.56
    jz
    0.55
     hypotheses
    0.54
     thicknesses
    0.52
     fillets
    0.52
    ニャ
    0.52
    thickness
    0.50
    ר
    0.50
    genes
    0.49
     muttered
    0.49
    Activations Density 0.000%

    No Known Activations