© 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. 110627
    Prev
    Next
    INDEX
    Explanations

    titles, functionality, tools, Thai, Korean

    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
     are
    1.50
    ро
    1.23
    s
    1.15
    다
    1.13
    ру
    1.09
     can
    1.08
    ses
    1.07
    та
    1.01
    া
    1.00
    swith
    0.99
    POSITIVE LOGITS
    W
    1.34
    H
    1.23
    O
    1.22
    X
    1.13
    ب
    1.09
    E
    1.03
    ৬
    1.02
    ’
    1.00
    M
    0.99
    F
    0.98
    Activations Density 0.000%

    No Known Activations