© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23140
    Prev
    Next
    INDEX
    Explanations

    high

    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_56_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
     pursue
    0.38
     pursuing
    0.38
     pursued
    0.37
    佉
    0.37
    h
    0.36
    HLER
    0.35
     pursuit
    0.34
    迫
    0.34
    hd
    0.34
     salient
    0.33
    POSITIVE LOGITS
     school
    1.14
    school
    1.11
    School
    1.00
    SCHOOL
    1.00
     SCHOOL
    0.98
     School
    0.96
     स्कूल
    0.89
    स्कूल
    0.82
     escola
    0.82
    école
    0.81
    Activations Density 0.001%

    No Known Activations