© 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. 110636
    Prev
    Next
    INDEX
    Explanations

    le syllable in various languages

    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
    R
    1.75
    S
    1.70
    K
    1.52
    O
    1.45
    M
    1.42
    P
    1.38
    H
    1.36
    E
    1.26
    F
    1.26
    T
    1.25
    POSITIVE LOGITS
    ים
    1.57
    다
    1.51
    ด
    1.41
    д
    1.36
    ओं
    1.32
    니
    1.30
    ের
    1.29
    לי
    1.27
    ד
    1.27
    ون
    1.24
    Activations Density 0.000%

    No Known Activations