© 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. 110548
    Prev
    Next
    INDEX
    Explanations

    birdman

    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
    T
    1.73
    A
    1.45
    P
    1.41
    l
    1.34
    D
    1.32
    C
    1.30
    -
    1.27
    i
    1.25
    G
    1.20
    EN
    1.20
    POSITIVE LOGITS
    у
    0.85
    营收
    0.77
    ουλ
    0.74
    ሢ
    0.74
    几
    0.73
    2
    0.73
    懂得
    0.72
     увеличения
    0.72
    在于
    0.71
    ᱒
    0.71
    Activations Density 0.000%

    No Known Activations