© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118385
    Prev
    Next
    INDEX
    Explanations

    thank you

    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_27_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
     kär
    0.40
    重视
    0.39
     énfasis
    0.38
    weil
    0.38
     আমিও
    0.38
     Arten
    0.37
     caminando
    0.37
    !}
    0.36
     favorito
    0.36
    leich
    0.36
    POSITIVE LOGITS
     rough
    0.42
    使
    0.41
     probably
    0.40
     identity
    0.40
     Probably
    0.40
     prevented
    0.39
     مقدار
    0.39
    Ὅ
    0.39
     sabbatical
    0.39
     originally
    0.38
    Activations Density 0.001%

    No Known Activations