© 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. 6674
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    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
     saying
    0.54
    한다
    0.45
     Saying
    0.44
    说
    0.44
     dizendo
    0.41
    getting
    0.39
    는다
    0.39
    說
    0.39
     한다
    0.38
     dicho
    0.38
    POSITIVE LOGITS
     ź
    0.38
    痘
    0.36
     gig
    0.36
    addresses
    0.36
    लन
    0.36
    态
    0.35
    ʙ
    0.35
     لكم
    0.35
    Angry
    0.34
    ₂)
    0.34
    Activations Density 0.000%

    No Known Activations