© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80281
    Prev
    Next
    INDEX
    Explanations

    really or very

    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
     mệnh
    0.38
     もう
    0.36
     पो
    0.35
     Rebellion
    0.35
     Position
    0.34
    াহত
    0.34
    宗
    0.34
     нанесе
    0.34
    ปล่อย
    0.34
    銜
    0.34
    POSITIVE LOGITS
    !»
    0.39
     khắp
    0.39
     pleases
    0.38
     Kwiatkowski
    0.38
     jól
    0.37
     Kw
    0.36
    Begriffsklär
    0.35
    uch
    0.34
     популяр
    0.34
     kv
    0.33
    Activations Density 0.024%

    No Known Activations