© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159704
    Prev
    Next
    INDEX
    Explanations

    possibility or potential action

    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_2_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
    ма
    1.86
    ي
    1.37
    не
    1.32
    د
    1.25
    માં
    1.24
    بي
    1.23
    ра
    1.22
    Penumpang
    1.21
    ನ
    1.20
    də
    1.15
    POSITIVE LOGITS
    0
    2.14
     for
    1.98
    et
    1.46
     (
    1.45
    )
    1.40
    }
    1.35
    8
    1.34
     with
    1.20
     {})
    1.17
     you
    1.13
    Activations Density 0.000%

    No Known Activations