© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174583
    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_20_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
     enviable
    0.44
    chol
    0.43
    ۷
    0.43
     गुलाबी
    0.43
    v
    0.43
    »,
    0.42
    SID
    0.42
    scrap
    0.42
     ፣
    0.42
    ചെയ
    0.41
    POSITIVE LOGITS
     instantiation
    0.51
     inscreva
    0.45
     nucleotides
    0.44
     nucleotide
    0.44
     lados
    0.43
    ხვევ
    0.43
     dimes
    0.42
     interstate
    0.42
     circonstances
    0.42
     causada
    0.41
    Activations Density 0.000%

    No Known Activations