© 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. 5740
    Prev
    Next
    INDEX
    Explanations

    is Opened

    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
    ించు
    0.38
     vig
    0.38
    }=\{
    0.37
     conditionally
    0.37
     Georgetown
    0.36
     Abbey
    0.34
     სპ
    0.34
    不出
    0.34
     tucked
    0.33
     рабо
    0.33
    POSITIVE LOGITS
    μά
    0.32
    IFICATE
    0.31
    きち
    0.31
    palette
    0.30
    坭
    0.30
    mux
    0.30
    DAG
    0.30
    opoe
    0.30
    ποι
    0.30
    faces
    0.29
    Activations Density 0.001%

    No Known Activations