© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80177
    Prev
    Next
    INDEX
    Explanations

    Russian Morse code or specific 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_0_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
    л
    2.02
    ل
    1.86
     synthes
    1.52
     an
    1.41
    !
    1.35
     decentral
    1.32
     been
    1.27
    ב
    1.27
    ك
    1.26
    p
    1.20
    POSITIVE LOGITS
    ج
    1.34
    ieurs
    1.27
    ación
    1.21
    ）,
    1.18
    ために
    1.16
     формы
    1.16
    -
    1.13
    人不
    1.12
    uğu
    1.09
    ச்சத்து
    1.09
    Activations Density 0.000%

    No Known Activations