© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174677
    Prev
    Next
    INDEX
    Explanations

    indicates likelihood or assumption

    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_24_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     prawdopod
    0.48
     likely
    0.42
    供应
    0.36
    帮
    0.36
    原因
    0.35
     Likely
    0.35
    ndes
    0.35
     일으
    0.34
     vox
    0.34
    likely
    0.34
    POSITIVE LOGITS
    था
    0.40
     Effectiveness
    0.39
    獎
    0.39
     жовтня
    0.39
     hospitalization
    0.38
     நுரைய
    0.38
     देणे
    0.38
     onions
    0.38
     प्याज
    0.37
    گذاری
    0.37
    Activations Density 0.014%

    No Known Activations