© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175679
    Prev
    Next
    INDEX
    Explanations

    repetition of words or sounds

    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_20_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
    COc
    0.40
     ہندوستان
    0.39
     femelle
    0.37
     المرحله
    0.37
    гли
    0.37
     நாக
    0.37
     CXCL
    0.37
    ൦
    0.37
     কলিক
    0.36
    ргә
    0.36
    POSITIVE LOGITS
     റേ
    0.40
     of
    0.38
    에게
    0.38
     usd
    0.38
     radi
    0.37
    any
    0.36
    Radi
    0.36
     wandering
    0.36
    lie
    0.36
    看法
    0.36
    Activations Density 0.005%

    No Known Activations