© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50068
    Prev
    Next
    INDEX
    Explanations

    repetition of words followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    \)
    0.38
     \)
    0.33
    で見
    0.33
     hein
    0.33
     enigma
    0.33
    従って
    0.33
     transferee
    0.32
     //-->
    0.32
     pauper
    0.32
    Damage
    0.32
    POSITIVE LOGITS
    繰り返
    0.42
    下去
    0.41
    不斷
    0.40
    repeated
    0.39
     मांगा
    0.38
     někol
    0.38
    不断
    0.38
    蜂蜜
    0.38
     sbagli
    0.38
    を聞
    0.38
    Activations Density 0.006%

    No Known Activations