© 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. 257672
    Prev
    Next
    INDEX
    Explanations

    before/after sequences

    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_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
     &_
    0.42
     सहित
    0.39
    fico
    0.39
     ಸೇರಿದ
    0.38
     સહિત
    0.37
    সহ
    0.36
     [{
    0.36
     них
    0.36
    सुन
    0.36
     समेत
    0.35
    POSITIVE LOGITS
     steadily
    0.35
    PRESSURE
    0.35
     whites
    0.34
    支
    0.34
     sépar
    0.34
    Google
    0.33
     riot
    0.33
    CCC
    0.33
    Wash
    0.33
    Va
    0.32
    Activations Density 0.000%

    No Known Activations