© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132533
    Prev
    Next
    INDEX
    Explanations

    jalapeño

    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_1_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
    1
    1.44
     are
    1.19
    0
    1.18
    to
    1.13
    8
    1.11
    }",
    1.05
    一
    1.03
    on
    1.02
    ت
    1.00
    with
    0.98
    POSITIVE LOGITS
    i
    1.16
    ו
    1.16
    ↵↵
    1.09
    ли
    1.08
    ناک
    1.05
    )
    1.05
     costo
    1.01
    ം
    0.99
    ?
    0.99
    ном
    0.96
    Activations Density 0.000%

    No Known Activations