© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59869
    Prev
    Next
    INDEX
    Explanations

    piston's mechanical action and parts

    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
            
    1.22
    EN
    1.19
    ET
    1.16
    AN
    1.09
     revital
    1.00
    rá
    0.92
    EL
    0.91
    رو
    0.91
    н
    0.91
     convirtió
    0.89
    POSITIVE LOGITS
    та
    1.48
    на
    1.31
    و
    1.29
    k
    1.23
    д
    1.20
    า
    1.19
    ่า
    1.14
    nya
    1.14
    of
    1.13
    ला
    1.13
    Activations Density 0.000%

    No Known Activations