© 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. 144963
    Prev
    Next
    INDEX
    Explanations

    preteen girl

    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
    I
    1.95
    1.51
    ر
    1.41
    -
    1.38
    E
    1.27
    ことです
    1.27
    กว่า
    1.20
     rápido
    1.18
    ás
    1.16
    IEN
    1.16
    POSITIVE LOGITS
     to
    1.63
    িন
    1.56
    to
    1.51
    та
    1.49
     Меня
    1.34
    يد
    1.32
    ի
    1.32
    ুল
    1.27
    ਾ
    1.27
    רי
    1.25
    Activations Density 0.000%

    No Known Activations