© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5887
    Prev
    Next
    INDEX
    Explanations

    say "in" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     বিকালে
    0.43
     বিকাল
    0.43
     evaporate
    0.41
     evaporates
    0.41
     ave
    0.40
     IN
    0.40
    蠵
    0.38
     Prozesse
    0.37
    kaa
    0.37
     progesterone
    0.37
    POSITIVE LOGITS
    ammation
    0.50
    encing
    0.47
    luence
    0.46
    imation
    0.44
    ਊ
    0.42
    uenza
    0.40
    fection
    0.39
     mainland
    0.38
    Vict
    0.38
    Bak
    0.38
    Activations Density 0.105%

    No Known Activations