Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 196719
    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_26_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
    ਬਰ
    0.50
    我有
    0.49
    Following
    0.46
     organise
    0.46
     opérateur
    0.46
     Concerns
    0.45
    電影
    0.44
    ن
    0.44
    roup
    0.43
    inaldo
    0.43
    POSITIVE LOGITS
     DateTime
    0.52
     esattamente
    0.51
    ேய
    0.45
    aky
    0.43
    ীতে
    0.42
    Daddy
    0.42
     कू
    0.42
     точно
    0.42
     Dayton
    0.42
     শিক্ষার্থীর
    0.42
    Activations Density 0.000%

    No Known Activations