© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214794
    Prev
    Next
    INDEX
    Explanations

    tweet based on summary

    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_5_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
    1.48
    ก
    1.12
    ל
    1.10
    ل
    1.09
    ر
    1.08
    ם
    1.07
    ร
    1.00
    یت
    0.99
    נ
    0.96
    ك
    0.93
    POSITIVE LOGITS
     as
    1.22
    es
    1.15
    রা
    1.07
    يد
    1.01
    ли
    0.98
     plastered
    0.98
    re
    0.96
    1
    0.94
    3
    0.91
    ري
    0.89
    Activations Density 0.024%

    No Known Activations