© 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. 127680
    Prev
    Next
    INDEX
    Explanations

    environmental, green, land, platforms, applications, Ket, silicon

    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
    ميل
    0.65
    مین
    0.61
    ją
    0.59
    $}
    0.59
     시간을
    0.58
    ர்கள்
    0.58
    مج
    0.58
     லட்சம்
    0.55
     வெளியே
    0.55
     년
    0.55
    POSITIVE LOGITS
    '
    0.71
    s
    0.68
     expon
    0.64
     happ
    0.63
     ident
    0.62
     for
    0.61
     livre
    0.60
     persen
    0.60
     missp
    0.60
     lym
    0.58
    Activations Density 0.000%

    No Known Activations