© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122155
    Prev
    Next
    INDEX
    Explanations

    test tubes upright

    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_3_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
    s
    1.16
    m
    0.86
    st
    0.75
    1
    0.75
    d
    0.75
    r
    0.73
    3
    0.70
    Test
    0.69
    stest
    0.69
    ed
    0.68
    POSITIVE LOGITS
    <0x0D>
    0.82
     innymi
    0.81
    نې
    0.80
    。</
    0.79
    \}=
    0.73
     możliwości
    0.73
    کي
    0.73
     incremento
    0.71
     vittime
    0.70
    یت
    0.69
    Activations Density 0.000%

    No Known Activations