© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156786
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    heavy
    0.51
     heavy
    0.50
    重
    0.45
     STRONG
    0.43
     schweren
    0.43
     strong
    0.41
     Heavy
    0.40
     těž
    0.40
     fuertes
    0.39
     güçlü
    0.39
    POSITIVE LOGITS
    रातील
    0.46
     abord
    0.39
     यूनियन
    0.38
    ⓘ
    0.37
    तोष
    0.37
     Tanzania
    0.36
    ალ
    0.35
    ыл
    0.35
     اتح
    0.35
    ילו
    0.35
    Activations Density 0.014%

    No Known Activations