© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211827
    Prev
    Next
    INDEX
    Explanations

    sorority, Brotherhood

    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
    ot
    1.20
    <0x0D>
    1.12
    ap
    1.11
     غیر
    1.10
    O
    1.10
    weapons
    1.09
    س
    1.09
    نی
    1.08
    وک
    1.07
    ’.
    1.05
    POSITIVE LOGITS
    on
    1.56
    其他
    1.52
    n
    1.48
    is
    1.42
    ية
    1.38
    ки
    1.22
    ด
    1.07
    ла
    1.02
    ,
    1.00
    ৬
    0.99
    Activations Density 0.000%

    No Known Activations