© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207576
    Prev
    Next
    INDEX
    Explanations

    talking

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     forwarded
    0.36
     पोलियो
    0.36
    flu
    0.35
     Flu
    0.35
     प्रेजेंट
    0.34
    Flu
    0.34
     implying
    0.34
    ·
    0.34
    Fa
    0.33
    备
    0.33
    POSITIVE LOGITS
     talking
    2.06
     talk
    1.94
    Talking
    1.88
     Talking
    1.86
    talking
    1.83
     Talk
    1.77
    Talk
    1.70
    talk
    1.66
     talked
    1.63
     berbicara
    1.60
    Activations Density 0.067%

    No Known Activations