© 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. 33719
    Prev
    Next
    INDEX
    Explanations

    Pulumi infrastructure as code

    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
     строй
    0.41
    xrightarrow
    0.38
     expos
    0.38
    ifs
    0.37
    Rising
    0.36
    Cxx
    0.36
    ις
    0.36
    विड
    0.35
    󠁧
    0.35
     Tyre
    0.35
    POSITIVE LOGITS
    usiasm
    0.46
    ách
    0.42
     hare
    0.41
    ாலம்
    0.41
    屈
    0.40
     ਕਰਨ
    0.39
    Hare
    0.39
     દ્વા
    0.38
     Freedman
    0.38
     compelled
    0.38
    Activations Density 0.001%

    No Known Activations