© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134038
    Prev
    Next
    INDEX
    Explanations

    get rich

    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_1_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
    ف
    1.37
    ק
    1.23
    ai
    1.19
    ן
    1.15
    та
    1.13
    ו
    1.08
     in
    1.05
    지
    1.05
     در
    1.03
    و
    1.03
    POSITIVE LOGITS
    した
    1.24
    1
    1.22
    ）
    1.09
     categor
    1.06
    ছিল
    1.02
    aided
    1.02
    ilación
    1.01
     hypothes
    1.00
    お
    0.98
    하는
    0.96
    Activations Density 0.002%

    No Known Activations