© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143851
    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_0_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
     Specifies
    0.58
     G
    0.55
     Whenever
    0.54
     Knowing
    0.54
     vært
    0.54
     q
    0.53
     Companies
    0.53
     menyatakan
    0.53
     Definition
    0.52
     ix
    0.51
    POSITIVE LOGITS
    ش
    0.67
    ج
    0.62
    트
    0.61
    ون
    0.59
    اد
    0.58
    자
    0.57
    سه
    0.57
    더
    0.57
    사
    0.55
    ड
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.