© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122811
    Prev
    Next
    INDEX
    Explanations

    EGI analytic continuation

    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_37_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
     analysts
    0.43
     recob
    0.40
     Analysts
    0.40
     digs
    0.39
     threw
    0.39
     акт
    0.38
    泳
    0.38
     trông
    0.38
     Analyst
    0.38
    recur
    0.38
    POSITIVE LOGITS
     Meister
    0.41
     वृ
    0.38
     multilevel
    0.38
     bucket
    0.37
     spleen
    0.36
     や
    0.36
     Spezial
    0.36
    bucket
    0.36
     precisam
    0.36
     Begriff
    0.36
    Activations Density 0.000%

    No Known Activations