© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233451
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     vyp
    0.48
    blox
    0.39
     ቢ
    0.39
    autop
    0.38
    Incre
    0.38
     Inet
    0.38
     liik
    0.37
    Tres
    0.37
     Tres
    0.37
     raí
    0.37
    POSITIVE LOGITS
     someday
    0.38
    蕞
    0.38
    akata
    0.36
    케이
    0.36
     RATE
    0.36
    ̔
    0.36
     같이
    0.35
     rate
    0.34
    சார
    0.33
    (",");
    0.33
    Activations Density 0.000%

    No Known Activations