© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207603
    Prev
    Next
    INDEX
    Explanations

    original code issues

    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_20_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
    MAY
    0.32
    ✶
    0.31
     genomes
    0.30
     partner
    0.29
    Pam
    0.29
     buch
    0.29
    Natal
    0.29
    Alaska
    0.29
    ❊
    0.29
    ancement
    0.28
    POSITIVE LOGITS
    掫
    0.33
    たり
    0.32
    排除
    0.31
     பெறு
    0.31
    簟
    0.30
     நடத்து
    0.29
     христи
    0.28
     ભારે
    0.28
     Inbetriebnahme
    0.28
    ამე
    0.28
    Activations Density 0.007%

    No Known Activations