© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164805
    Prev
    Next
    INDEX
    Explanations

    date and birth format

    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_31_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
     ጭ
    0.35
    subscriber
    0.33
     توانائی
    0.33
     volupt
    0.32
     Subscriber
    0.32
     settler
    0.32
     Lover
    0.32
     voidaan
    0.32
     operator
    0.31
     savun
    0.31
    POSITIVE LOGITS
    Clo
    0.39
     leaks
    0.35
     Clo
    0.35
     पो
    0.35
    ⚜
    0.34
    clo
    0.34
    anos
    0.33
    warm
    0.33
     रवा
    0.33
    Ethoxy
    0.33
    Activations Density 0.016%

    No Known Activations