© 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. 61769
    Prev
    Next
    INDEX
    Explanations

    hague, hait, holder

    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
    ও
    1.80
     in
    1.68
    も
    1.64
    도
    1.58
     در
    1.55
    は
    1.53
     σε
    1.49
    ۔
    1.48
    는
    1.43
     в
    1.42
    POSITIVE LOGITS
    et
    1.66
    st
    1.38
    ah
    1.38
    ai
    1.36
    for
    1.32
    av
    1.31
    as
    1.30
    b
    1.30
    ur
    1.30
    us
    1.27
    Activations Density 0.000%

    No Known Activations