© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62516
    Prev
    Next
    INDEX
    Explanations

    aiming at

    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_11_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
    1
    0.80
    3
    0.71
    OC
    0.71
    6
    0.68
    9
    0.66
    an
    0.66
    CEO
    0.66
    5
    0.66
    AM
    0.64
    f
    0.64
    POSITIVE LOGITS
     agitated
    0.66
     ANIM
    0.65
     térm
    0.64
    ificada
    0.63
     άνθρω
    0.61
     கலைஞ
    0.60
    isateur
    0.59
     اصحاب
    0.59
     Ambiental
    0.58
     indignant
    0.58
    Activations Density 0.000%

    No Known Activations