© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136212
    Prev
    Next
    INDEX
    Explanations

    Backend-as-a-Service (BaaS)

    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_12_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
    =$
    0.44
     pigments
    0.41
    Opacity
    0.39
     =
    0.38
     годах
    0.38
    ",
    0.38
    Gujarat
    0.38
    ":
    0.38
    ът
    0.36
    t
    0.36
    POSITIVE LOGITS
    esch
    0.39
     Fernandez
    0.39
     regime
    0.38
     raref
    0.38
    វា
    0.36
    ppet
    0.36
     Rogers
    0.36
     permitem
    0.36
     Farrell
    0.36
     Larry
    0.35
    Activations Density 0.000%

    No Known Activations