© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16270
    Prev
    Next
    INDEX
    Explanations

    decoding text outputs

    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_40_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
    accord
    0.39
    坯
    0.39
    音樂
    0.38
     Thương
    0.38
     সরকারী
    0.38
    陼
    0.38
     rispondere
    0.37
    र्भ
    0.37
    鄭
    0.37
    lains
    0.37
    POSITIVE LOGITS
     steward
    0.43
     hint
    0.39
    pairwise
    0.39
    ජ
    0.37
     ctx
    0.36
     ass
    0.36
     Steward
    0.36
     HttpException
    0.36
     pairwise
    0.35
    ologisch
    0.35
    Activations Density 0.000%

    No Known Activations