© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100552
    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_14_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
    Uma
    0.54
    label
    0.53
    ну
    0.52
    Anche
    0.52
    desired
    0.51
    language
    0.50
    Ве
    0.50
    <0x0D>
    0.50
    子供
    0.50
    Otro
    0.50
    POSITIVE LOGITS
     র
    0.51
     ذه
    0.50
     asymmetries
    0.50
     rigidity
    0.49
     punctures
    0.49
     heuristics
    0.49
     technologies
    0.46
     ratios
    0.46
     slides
    0.46
    ங்க்
    0.46
    Activations Density 0.000%

    No Known Activations