© 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. 260862
    Prev
    Next
    INDEX
    Explanations

    elytron, dialog, transparent

    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
     of
    1.06
    t
    1.05
    )
    1.03
    (
    0.98
    an
    0.97
    ]
    0.95
    \
    0.95
    2
    0.89
    _
    0.89
    v
    0.88
    POSITIVE LOGITS
    с
    0.95
    ба
    0.90
    ট
    0.89
    та
    0.88
    в
    0.87
    ना
    0.84
    스
    0.83
    وم
    0.81
    ну
    0.80
    ي
    0.79
    Activations Density 0.000%

    No Known Activations