© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171017
    Prev
    Next
    INDEX
    Explanations

    python versions and linux distributions

    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_20_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
     ČR
    0.45
     учили
    0.44
    чают
    0.42
     surgi
    0.41
    ,$$
    0.41
    malıdır
    0.40
    必要があります
    0.40
     chiuso
    0.40
    ਹਾ
    0.40
     asesor
    0.40
    POSITIVE LOGITS
     advantages
    0.45
    Green
    0.44
    \
    0.43
     عط
    0.43
     உற்ச
    0.43
     المت
    0.42
     మె
    0.41
    instead
    0.41
     ভালবাস
    0.40
    Pablo
    0.40
    Activations Density 0.001%

    No Known Activations