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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196158
    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
    lardır
    0.45
    俩
    0.41
    囦
    0.38
    jersey
    0.37
    mayın
    0.37
     فوج
    0.37
    嬷
    0.37
    为了
    0.36
    高兴
    0.36
     khổ
    0.36
    POSITIVE LOGITS
     thor
    0.46
     oor
    0.45
     th
    0.44
    Aff
    0.44
    azim
    0.44
    agge
    0.43
    cgColor
    0.43
     runat
    0.43
     amassed
    0.42
    angor
    0.42
    Activations Density 0.000%

    No Known Activations