© 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. 26921
    Prev
    Next
    INDEX
    Explanations

    nothing happens

    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
    Not in Any Lists

    No Comments

    Negative Logits
    lineWidth
    0.38
    think
    0.38
    Q
    0.38
     THINK
    0.37
     मोह
    0.35
     raisin
    0.35
    준
    0.35
    టీఎం
    0.34
    綾
    0.34
    рав
    0.34
    POSITIVE LOGITS
     sil
    0.47
    aap
    0.41
     Sil
    0.41
     Subscribe
    0.40
     AAP
    0.40
     subscribe
    0.39
     desto
    0.38
     GUID
    0.38
     Simultaneous
    0.37
     significance
    0.37
    Activations Density 0.022%

    No Known Activations