© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59398
    Prev
    Next
    INDEX
    Explanations

    being + verb

    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_2_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
    a
    1.14
    ीत
    0.96
    ed
    0.96
    el
    0.95
    H
    0.95
    ills
    0.91
    -
    0.91
     I
    0.91
    ic
    0.90
    EL
    0.88
    POSITIVE LOGITS
     be
    1.47
    מ
    1.13
    ب
    1.13
    jší
    1.10
    প
    1.06
    נ
    1.06
    ä
    1.05
    ৪
    1.02
     as
    0.98
    不會
    0.98
    Activations Density 0.000%

    No Known Activations