© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215918
    Prev
    Next
    INDEX
    Explanations

    Here

    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_47_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
    picklist
    0.43
     العلم
    0.40
    ﻨ
    0.39
    嘖
    0.36
     कब
    0.36
    োনো
    0.36
    Hend
    0.35
     Conquer
    0.35
    blah
    0.34
    iology
    0.34
    POSITIVE LOGITS
    IntegerField
    0.44
     square
    0.43
     Square
    0.41
     የግ
    0.40
     cuts
    0.40
     Chir
    0.39
     Gazi
    0.38
    雬
    0.38
    Pooling
    0.38
     Cuts
    0.38
    Activations Density 0.010%

    No Known Activations