© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59198
    Prev
    Next
    INDEX
    Explanations

    red-black tree

    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_11_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
     pedestrians
    0.25
    চন্দ্রের
    0.25
    iliśmy
    0.25
    <unused18>
    0.25
     pleinement
    0.24
    сения
    0.24
    ธรรมชาติ
    0.24
    तिहासिक
    0.23
    <unused16>
    0.23
     startled
    0.23
    POSITIVE LOGITS
    al
    0.32
    f
    0.26
    d
    0.26
    ad
    0.25
    \
    0.25
    po
    0.24
    s
    0.24
    ch
    0.24
     \
    0.24
    t
    0.24
    Activations Density 0.008%

    No Known Activations