© 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. 112945
    Prev
    Next
    INDEX
    Explanations

    Hard-Boiled

    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
    ש
    1.62
    ه
    1.59
    f
    1.45
    us
    1.42
    ро
    1.38
    ad
    1.30
    ה
    1.24
    ن
    1.23
    id
    1.22
    st
    1.21
    POSITIVE LOGITS
    是
    1.23
    は
    1.10
    ۲
    0.97
    이면
    0.92
    는
    0.88
     on
    0.88
     provoz
    0.86
    은
    0.86
     불구하고
    0.84
    會
    0.84
    Activations Density 0.001%

    No Known Activations