© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207479
    Prev
    Next
    INDEX
    Explanations

    assert statements

    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_20_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
    OKA
    0.45
    OGRAM
    0.45
    bandSize
    0.45
    MiddleLine
    0.44
     مختلف
    0.43
    ोत
    0.43
    ﮩ
    0.43
    (",",
    0.43
    issage
    0.42
    CartVO
    0.42
    POSITIVE LOGITS
     G
    0.51
     Year
    0.50
     कंप्र
    0.48
     P
    0.44
     साइन
    0.44
     W
    0.43
     crear
    0.43
    接到
    0.43
     tạo
    0.43
     other
    0.42
    Activations Density 0.000%

    No Known Activations