© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42152
    Prev
    Next
    INDEX
    Explanations

    many followed by people/groups

    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_22_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
    编译器
    0.39
    犟
    0.39
     mêmes
    0.39
    ⓓ
    0.39
    တိ
    0.38
    姮
    0.38
    明显的
    0.38
    ᵍ
    0.38
     restante
    0.37
     .)
    0.37
    POSITIVE LOGITS
     относится
    0.43
     причем
    0.42
     рассказывает
    0.39
    🏖
    0.39
    unfortunately
    0.39
     recomend
    0.39
     pea
    0.38
     Slavic
    0.38
     актер
    0.38
     unfortunately
    0.38
    Activations Density 0.005%

    No Known Activations