© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213513
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     diseg
    0.39
     lhe
    0.39
    Synth
    0.38
     ሰ
    0.37
     McD
    0.37
     ലഭ
    0.37
    内地
    0.37
     subsid
    0.37
     میکرز
    0.36
    甲
    0.36
    POSITIVE LOGITS
     CEA
    0.44
     pau
    0.41
     Fuer
    0.41
    Jo
    0.40
     Ria
    0.40
     Announcement
    0.39
     сту
    0.38
     Jo
    0.38
    Announcement
    0.38
     NTE
    0.38
    Activations Density 0.001%

    No Known Activations