© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193086
    Prev
    Next
    INDEX
    Explanations

    texmaker

    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_4_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
     \
    1.13
     Texas
    1.05
    k
    1.05
     Been
    1.00
     I
    0.98
    h
    0.96
    j
    0.89
     texas
    0.89
    '
    0.88
    ll
    0.86
    POSITIVE LOGITS
    та
    1.73
    ای
    1.54
    т
    1.47
    ینگ
    1.22
    ン
    1.20
    ਰ
    1.17
    ν
    1.14
    ला
    1.13
    یا
    1.12
    ٹ
    1.09
    Activations Density 0.001%

    No Known Activations