© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108050
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    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_1_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
    ER
    1.83
    O
    1.44
    ot
    1.38
    هاي
    1.30
    OS
    1.19
    د
    1.19
    ен
    1.13
    म
    1.09
    д
    1.09
    ↵↵
    1.07
    POSITIVE LOGITS
    p
    1.82
    s
    1.49
    t
    1.45
    r
    1.39
    a
    1.37
    n
    1.31
    with
    1.23
    x
    1.15
    payment
    1.10
    pets
    1.09
    Activations Density 0.003%

    No Known Activations