© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22260
    Prev
    Next
    INDEX
    Explanations

    global/national

    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
    ब्बे
    0.42
    jwa
    0.38
    ManagerPortal
    0.37
    odimensional
    0.36
    มีความ
    0.36
    ຄວາມ
    0.36
    溥
    0.35
    मानुसार
    0.35
    શો
    0.33
    ऱ
    0.33
    POSITIVE LOGITS
    Glob
    1.47
    glob
    1.44
    Intern
    1.43
     Nation
    1.43
    intern
    1.37
     Internation
    1.29
     Intern
    1.23
    Extern
    1.20
     nation
    1.20
    Nation
    1.20
    Activations Density 1.077%

    No Known Activations