© 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. 38219
    Prev
    Next
    INDEX
    Explanations

    fully-fledged

    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
     as
    0.91
     is
    0.79
    is
    0.78
    انی
    0.76
     व
    0.74
    اً
    0.71
    на
    0.70
    .)
    0.66
     was
    0.66
    of
    0.64
    POSITIVE LOGITS
     izdel
    0.67
    chief
    0.65
    ccedil
    0.64
     acessórios
    0.63
     in
    0.63
     dhinak
    0.63
     صہیونیت
    0.63
    keras
    0.61
    calup
    0.61
     saddhim
    0.61
    Activations Density 0.007%

    No Known Activations