© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260946
    Prev
    Next
    INDEX
    Explanations

    bed before, bed bound, to bed

    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_5_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
    ä
    1.20
    í
    1.12
    iert
    0.99
    ?
    0.99
    ва
    0.98
    f
    0.95
     réellement
    0.93
    ാ
    0.92
     établ
    0.91
    ación
    0.91
    POSITIVE LOGITS
    AK
    1.50
    ES
    1.47
    та
    1.44
    つ
    1.42
    이면
    1.41
    의
    1.34
    on
    1.28
    US
    1.28
    Y
    1.28
    の
    1.27
    Activations Density 0.001%

    No Known Activations