© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261950
    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_22_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
     жыл
    0.46
     forskj
    0.44
     رکھنا
    0.43
    houden
    0.42
     büyü
    0.42
     parete
    0.42
    耿
    0.42
     anschließend
    0.41
     rosto
    0.40
     பண்ண
    0.40
    POSITIVE LOGITS
     cod
    0.41
     state
    0.39
      
    0.38
     Cod
    0.38
    translator
    0.38
    state
    0.37
    .}$
    0.37
    as
    0.37
     indicated
    0.37
     recognize
    0.37
    Activations Density 0.000%

    No Known Activations