© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36838
    Prev
    Next
    INDEX
    Explanations

    location Swift building

    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_11_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
    Mw
    0.58
    )=(-
    0.57
    $，
    0.56
    )【
    0.55
    ,【
    0.55
    𝙎
    0.54
     kwamba
    0.54
    MessageNow
    0.53
    HAD
    0.53
    S
    0.52
    POSITIVE LOGITS
    ang
    0.64
     ME
    0.57
    is
    0.55
    </tr>
    0.53
     hidup
    0.53
     elabor
    0.51
    ৫
    0.51
    ри
    0.50
     pict
    0.50
     عدم
    0.50
    Activations Density 0.001%

    No Known Activations