© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159408
    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_2_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
    ون
    1.63
    that
    1.38
    om
    1.27
     that
    1.21
    ur
    1.20
    ik
    1.17
    or
    1.16
    ه
    1.13
    ning
    1.11
    ion
    1.05
    POSITIVE LOGITS
    な
    0.91
     था
    0.87
     beş
    0.83
    n
    0.83
    áš
    0.82
    پيديا
    0.82
     हालाँकि
    0.82
     feudal
    0.81
    ╅
    0.81
    ᱶ
    0.81
    Activations Density 0.000%

    No Known Activations