© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122517
    Prev
    Next
    INDEX
    Explanations

    too + adjective/adverb

    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_3_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
    t
    1.15
    ت
    1.04
    h
    0.94
    یر
    0.91
    т
    0.89
    تهم
    0.88
    tR
    0.85
    ли
    0.79
    c
    0.75
    ೊ
    0.73
    POSITIVE LOGITS
    ;
    1.25
    '
    0.96
    >
    0.89
    ０
    0.75
    {
    0.74
     kuid
    0.73
    \
    0.73
    =
    0.73
    -\
    0.72
    지
    0.72
    Activations Density 0.005%

    No Known Activations