© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103961
    Prev
    Next
    INDEX
    Explanations

    memoria

    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_1_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
    -
    1.34
    .
    1.15
     wie
    1.09
    '
    1.02
    是
    1.02
    ína
    0.97
    ération
    0.91
    ós
    0.90
     dalla
    0.89
    isant
    0.88
    POSITIVE LOGITS
    מ
    1.43
    <0x80>
    1.31
    ג
    1.19
    то
    1.16
    م
    1.16
    м
    1.16
    ס
    1.15
    ור
    1.14
    ты
    1.13
    m
    1.09
    Activations Density 0.001%

    No Known Activations