© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165679
    Prev
    Next
    INDEX
    Explanations

    `your` path replacement

    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_34_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
     ತೆಗೆ
    0.43
     adapts
    0.41
    ดูแล
    0.40
    ണമെന്ന്
    0.40
    匾
    0.38
    ल्पनिक
    0.38
    শনার
    0.37
    ቱ
    0.37
     PREFIX
    0.37
    照顧
    0.37
    POSITIVE LOGITS
     adam
    0.38
    atz
    0.36
     asp
    0.35
    힘
    0.35
     wh
    0.34
     görüntü
    0.34
    hent
    0.33
    گان
    0.33
    €™
    0.32
     simultaneously
    0.32
    Activations Density 0.005%

    No Known Activations