© 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. 110469
    Prev
    Next
    INDEX
    Explanations

    reissuing or reissuance

    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
     as
    1.30
    el
    1.29
    ul
    1.27
     are
    1.23
    ер
    1.15
    с
    1.11
    ir
    1.09
     do
    1.05
     war
    1.05
     can
    1.05
    POSITIVE LOGITS
    the
    1.38
    t
    1.34
    ０
    1.02
    ?
    1.02
    '.
    0.97
    thed
    0.97
    \
    0.97
    라
    0.95
    ק
    0.95
    fZ
    0.95
    Activations Density 0.000%

    No Known Activations