© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37332
    Prev
    Next
    INDEX
    Explanations

    sounds

    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_57_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
    𝗼
    0.46
    𝕐
    0.39
    So
    0.39
    𝘰
    0.39
     SO
    0.36
    utives
    0.36
    KeyState
    0.36
    apatkan
    0.35
    ô
    0.35
    হাম্ম
    0.35
    POSITIVE LOGITS
     soc
    0.95
     sod
    0.95
     dow
    0.93
     som
    0.89
     sop
    0.85
     dom
    0.83
     sog
    0.82
     dot
    0.82
     Dow
    0.81
     sot
    0.81
    Activations Density 0.045%

    No Known Activations