© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56893
    Prev
    Next
    INDEX
    Explanations

    examples starting with e.g

    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_11_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
     HPV
    0.63
    an
    0.63
    jeta
    0.63
     প্রতিহিংস
    0.61
    าด
    0.60
    R
    0.60
     offend
    0.60
     enrolling
    0.60
     грошы
    0.60
    oje
    0.59
    POSITIVE LOGITS
     was
    0.66
     Wasn
    0.63
    ற்புத
    0.54
     resonates
    0.54
    만
    0.52
     Determines
    0.52
     is
    0.49
    springframework
    0.47
    ቕ
    0.47
    lassical
    0.46
    Activations Density 0.009%

    No Known Activations