© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109161
    Prev
    Next
    INDEX
    Explanations

    mapped, gapped, chapped, overlapped

    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
    is
    1.35
    া
    1.35
    ת
    1.25
    ва
    1.23
    ه
    1.23
    ución
    1.02
    는
    1.02
    ъм
    0.99
    for
    0.98
     אנ
    0.98
    POSITIVE LOGITS
    I
    1.52
     in
    1.45
    Y
    1.41
    s
    1.33
    It
    1.27
    In
    1.27
    That
    1.23
    \
    1.21
    在
    1.20
    ILL
    1.16
    Activations Density 0.001%

    No Known Activations