© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33582
    Prev
    Next
    INDEX
    Explanations

    speaking languages

    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     नवे
    0.35
     irreducible
    0.34
    elere
    0.33
    важа
    0.33
    iply
    0.32
    ᒍ
    0.32
     survey
    0.32
     alc
    0.32
    িত্ব
    0.32
    }$;
    0.31
    POSITIVE LOGITS
     speak
    2.84
     speaks
    2.61
     Speak
    2.61
    Speak
    2.53
     speaking
    2.50
    speak
    2.48
     spoke
    2.31
     SPEAK
    2.31
    speaking
    2.28
     Speaking
    2.22
    Activations Density 0.149%

    No Known Activations