© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78592
    Prev
    Next
    INDEX
    Explanations

    Wireshark

    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_0_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
    -
    1.96
    `}
    1.63
    '
    1.61
    EN
    1.42
    n
    1.38
    '?
    1.34
    '.
    1.30
    يمكن
    1.30
    ET
    1.28
    '}
    1.27
    POSITIVE LOGITS
     on
    1.93
    of
    1.46
    ۹
    1.41
    ی
    1.39
    다
    1.38
     one
    1.34
    י
    1.28
    ढ़ाई
    1.25
    時に
    1.23
    ﻭ
    1.23
    Activations Density 0.001%

    No Known Activations