© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195741
    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_4_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
    ٠
    0.52
    0.46
    vering
    0.44
    结算
    0.44
    〇
    0.42
    langle
    0.42
    Estos
    0.42
    市值
    0.41
    他
    0.41
    故
    0.41
    POSITIVE LOGITS
    ша
    0.57
    یم
    0.57
    ک
    0.55
    یس
    0.55
    uanya
    0.55
    िया
    0.54
    ेल
    0.54
    েল
    0.54
    ิค
    0.53
    ะ
    0.52
    Activations Density 0.000%

    No Known Activations