© 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. 133681
    Prev
    Next
    INDEX
    Explanations

    refreshing

    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
    l
    1.71
    is
    1.51
    th
    1.49
    en
    1.41
    the
    1.38
    ai
    1.30
    s
    1.27
    st
    1.24
    of
    1.20
    la
    1.20
    POSITIVE LOGITS
    נה
    1.07
    >());
    1.04
     amely
    0.97
     hemicontinuous
    0.93
     categor
    0.91
     avem
    0.90
    ﺏ
    0.90
    Ᏸ
    0.90
    ánico
    0.89
     jeopard
    0.88
    Activations Density 0.000%

    No Known Activations