© 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. 134416
    Prev
    Next
    INDEX
    Explanations

    whirling, europe, peptides

    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
    ب
    2.20
    م
    2.05
    м
    1.55
    в
    1.46
    u
    1.42
    is
    1.41
    ات
    1.40
    나
    1.34
    an
    1.32
    ر
    1.25
    POSITIVE LOGITS
     i
    1.18
     ende
    1.00
    pathy
    0.98
    st
    0.93
     aren
    0.91
     aria
    0.90
     and
    0.88
    রামর্শ
    0.86
     envoy
    0.85
     Heavenly
    0.84
    Activations Density 0.000%

    No Known Activations