© 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. 157805
    Prev
    Next
    INDEX
    Explanations

    Yong followed by names or places

    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
    -
    1.13
     jeopard
    1.07
    ál
    1.01
    ávat
    0.96
    리
    0.93
    Е
    0.93
    有着
    0.91
    וד
    0.91
    lük
    0.91
    ৫
    0.91
    POSITIVE LOGITS
    u
    1.45
     from
    1.41
    al
    1.21
    1
    1.13
    ingredients
    1.10
    the
    1.09
    ви
    1.05
     for
    1.02
    сё
    1.02
    ized
    1.01
    Activations Density 0.000%

    No Known Activations