© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254127
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    supported
    0.45
    Loved
    0.39
    preferred
    0.37
    Supported
    0.35
    intero
    0.34
    Lips
    0.33
    ——
    0.32
    ocatore
    0.32
    怒
    0.32
    댐
    0.32
    POSITIVE LOGITS
     shedding
    0.48
     CEA
    0.44
    সিংহ
    0.41
     Lehrer
    0.41
     cấp
    0.40
     Speech
    0.40
     trafficking
    0.40
     ceb
    0.40
     पढ़कर
    0.40
     ज्ञापन
    0.39
    Activations Density 0.000%

    No Known Activations