© 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. 41101
    Prev
    Next
    INDEX
    Explanations

    leaves or falafel

    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
    는
    0.73
    のための
    0.70
     که
    0.68
    व
    0.68
    その
    0.67
     cenderung
    0.67
    いろんな
    0.66
     माहिती
    0.66
     cocok
    0.65
     pikiran
    0.65
    POSITIVE LOGITS
    يد
    0.78
     ليس
    0.70
     for
    0.70
     ఇంటి
    0.68
    ني
    0.68
    يني
    0.65
    مكن
    0.65
    ва
    0.64
    {
    0.63
    رك
    0.63
    Activations Density 0.002%

    No Known Activations