© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227807
    Prev
    Next
    INDEX
    Explanations

    year numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    ：
    0.93
    保管
    0.71
    。“
    0.68
     conductance
    0.67
    涵
    0.66
    ：（
    0.65
    ваме
    0.64
    ﮈ
    0.63
    ስቃ
    0.63
    ﻜ
    0.63
    POSITIVE LOGITS
    ;
    1.01
    \
    1.00
     Asturias
    0.92
     \
    0.91
    0
    0.91
    ",
    0.91
    u
    0.90
    ש
    0.88
    "),
    0.86
    n
    0.85
    Activations Density 0.007%

    No Known Activations