© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 144841
    Prev
    Next
    INDEX
    Explanations

    pn followed by specific characters

    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
    ing
    2.41
    0
    1.73
    ة
    1.68
    to
    1.62
    ،
    1.61
    g
    1.52
    c
    1.51
    ine
    1.44
     a
    1.31
    ins
    1.25
    POSITIVE LOGITS
    ن
    2.31
    ي
    1.91
    나
    1.72
    ని
    1.69
    น
    1.68
    न
    1.67
    리
    1.61
    ն
    1.52
    드
    1.52
    사
    1.51
    Activations Density 0.000%

    No Known Activations