© 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. 84225
    Prev
    Next
    INDEX
    Explanations

    surprise followed by detail

    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
     for
    1.99
    д
    1.75
    UR
    1.42
    )،
    1.41
     can
    1.39
     \
    1.35
    스
    1.27
    AD
    1.26
    AU
    1.23
    "،
    1.22
    POSITIVE LOGITS
    il
    1.59
    on
    1.55
    ता
    1.39
    is
    1.36
    是
    1.31
    ር
    1.28
     on
    1.27
    なります
    1.23
    عاد
    1.23
    ની
    1.19
    Activations Density 0.007%

    No Known Activations