© 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. 110151
    Prev
    Next
    INDEX
    Explanations

    LoRaWAN

    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
    <
    1.20
    ).
    1.12
     be
    1.06
    CT
    1.04
    ON
    1.03
    AN
    1.01
     Department
    0.99
    >
    0.99
    AT
    0.98
     not
    0.96
    POSITIVE LOGITS
    ни
    1.52
    s
    1.49
    ির
    1.47
    ים
    1.34
    ي
    1.27
    ের
    1.26
    z
    1.26
    な
    1.23
    ی
    1.20
    ет
    1.20
    Activations Density 0.000%

    No Known Activations