© 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. 104411
    Prev
    Next
    INDEX
    Explanations

    stagnation

    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
     you
    1.34
    ת
    1.31
    an
    1.30
    ir
    1.27
    y
    1.24
    ,"
    1.23
    a
    1.18
    ל
    1.14
    u
    1.13
    на
    1.12
    POSITIVE LOGITS
    <h3>
    1.13
    <h4>
    1.09
    <h1>
    0.95
    даги
    0.91
    šno
    0.89
     разрабо
    0.88
    <h5>
    0.88
     badger
    0.84
     microprocessor
    0.83
     regra
    0.83
    Activations Density 0.000%

    No Known Activations