© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61156
    Prev
    Next
    INDEX
    Explanations

    water quality

    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_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
    á
    1.47
    로
    1.30
    í
    1.29
    ,\
    1.16
    ،
    1.09
    ون
    1.09
    \
    1.09
    은
    1.09
    ，
    1.04
     It
    1.02
    POSITIVE LOGITS
    0
    1.48
    ش
    1.23
    ↵
    1.11
    the
    1.06
    for
    1.00
    ন
    1.00
     primate
    0.99
     for
    0.94
    ার
    0.94
    م
    0.94
    Activations Density 0.000%

    No Known Activations