© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162366
    Prev
    Next
    INDEX
    Explanations

    tightly coupled

    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
    s
    1.85
    </h2>
    1.48
    </h3>
    1.34
    AL
    1.33
    <0x0D>
    1.29
    </h1>
    1.22
    AN
    1.20
    EN
    1.19
    RE
    1.18
    IL
    1.18
    POSITIVE LOGITS
    x
    1.39
     август
    1.32
    ۰
    1.27
    bindingFields
    1.25
    can
    1.23
    на
    1.18
     апре
    1.16
    ಗಾಗಿ
    1.14
    ۹
    1.14
    اي
    1.12
    Activations Density 0.001%

    No Known Activations