© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192920
    Prev
    Next
    INDEX
    Explanations

    coconut

    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_4_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
    기
    0.96
     IMS
    0.89
     ITIS
    0.89
     innych
    0.88
     Ι
    0.83
     AutoML
    0.83
     interfere
    0.83
     ISS
    0.82
     Κ
    0.82
     IDEA
    0.82
    POSITIVE LOGITS
    apping
    1.13
    ۔
    1.13
    י
    1.11
    ።
    1.04
    <0xAB>
    0.97
    。
    0.95
    de
    0.95
    ння
    0.94
    ação
    0.92
    of
    0.91
    Activations Density 0.002%

    No Known Activations