© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82595
    Prev
    Next
    INDEX
    Explanations

    pronunciation guides

    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_0_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
    し
    2.06
    ac
    1.60
    ل
    1.59
    ться
    1.45
    jší
    1.37
    י
    1.29
    padă
    1.28
    ි
    1.27
    보는
    1.24
    മ
    1.22
    POSITIVE LOGITS
    )
    1.77
    (
    1.55
    :
    1.48
    ın
    1.48
    ’
    1.34
    ς
    1.27
    ,
    1.25
    =
    1.21
    )’
    1.20
    ের
    1.17
    Activations Density 0.001%

    No Known Activations