© 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. 109563
    Prev
    Next
    INDEX
    Explanations

    e followed by r

    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
    一
    1.33
    ك
    1.24
    onavírus
    1.23
    보
    1.21
    아
    1.19
    大
    1.16
    କ
    1.16
    به
    1.12
    ket
    1.09
    分享
    1.09
    POSITIVE LOGITS
    r
    1.55
    '
    1.28
    s
    1.20
    ים
    1.16
    ların
    1.16
    لای
    1.10
    لین
    1.09
    la
    1.08
    м
    1.08
    с
    1.07
    Activations Density 0.000%

    No Known Activations