© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57946
    Prev
    Next
    INDEX
    Explanations

    form.get, errors

    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_11_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
    LEY
    0.50
    ਲ
    0.45
    OTROS
    0.44
    銠
    0.43
    <0xBE>
    0.43
     láser
    0.43
     மருந்த
    0.42
    劻
    0.42
    滏
    0.42
     elétrica
    0.42
    POSITIVE LOGITS
     probationary
    0.50
    size
    0.46
    expected
    0.46
    present
    0.45
    with
    0.44
     executor
    0.44
    indications
    0.44
    executor
    0.43
    text
    0.42
    the
    0.42
    Activations Density 0.021%

    No Known Activations