© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34256
    Prev
    Next
    INDEX
    Explanations

    chalet, charizard, chaldeans

    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_3_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
    <0x80>
    0.89
    0
    0.82
     fenders
    0.73
    㞓
    0.73
    ó
    0.72
     ballast
    0.70
    0.68
     pallets
    0.68
     провер
    0.67
     nó
    0.67
    POSITIVE LOGITS
    is
    1.22
    ch
    1.03
    v
    1.03
    ל
    0.92
    st
    0.88
    ור
    0.86
    ar
    0.85
    c
    0.84
    きた
    0.83
    ні
    0.81
    Activations Density 0.003%

    No Known Activations