© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237559
    Prev
    Next
    INDEX
    Explanations

    code completion

    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_32_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
     sideWeight
    0.40
    Residence
    0.38
     Format
    0.36
    実装
    0.36
     Residence
    0.36
     ;(
    0.36
    Cad
    0.36
     outward
    0.35
    ">&
    0.35
    做了
    0.35
    POSITIVE LOGITS
     рӯ
    0.39
    prompt
    0.38
     sicuro
    0.37
     село
    0.36
    ioutil
    0.36
     révèle
    0.36
     prompt
    0.36
     faudra
    0.35
     구분
    0.35
     dissect
    0.35
    Activations Density 0.001%

    No Known Activations