© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22875
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     }],
    0.34
    ꔹ
    0.34
    urized
    0.33
    ownic
    0.33
     karm
    0.33
    涜
    0.33
    typicode
    0.32
     მიმოწერა
    0.32
    裴
    0.32
    鱉
    0.32
    POSITIVE LOGITS
     C
    2.52
    C
    2.22
     c
    2.11
    <0x83>
    1.74
    Ｃ
    1.68
     الص
    1.65
    c
    1.63
     ص
    1.49
    setC
    1.46
    𝐶
    1.42
    Activations Density 0.028%

    No Known Activations