© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198526
    Prev
    Next
    INDEX
    Explanations

    say "You"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    纱
    0.41
     Dünya
    0.38
     Stream
    0.38
     Tạo
    0.36
    JSX
    0.35
     ત્યારબાદ
    0.35
    をして
    0.35
    antium
    0.35
    Ꮧ
    0.35
    STAGE
    0.34
    POSITIVE LOGITS
     Oed
    0.38
     lij
    0.38
     Christians
    0.38
    erode
    0.36
    chanics
    0.35
    cccs
    0.35
    ቝ
    0.35
     Plains
    0.35
    offsetWidth
    0.35
     깊
    0.34
    Activations Density 0.002%

    No Known Activations