© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57098
    Prev
    Next
    INDEX
    Explanations

    exclamations followed by words

    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
    h
    0.48
    لڈ
    0.43
    🅽
    0.42
    ငန်း
    0.40
    ет
    0.40
    ЕТ
    0.38
    là
    0.38
    λογία
    0.38
    ется
    0.37
    ależy
    0.37
    POSITIVE LOGITS
     (
    0.61
     (“
    0.45
     I
    0.44
     l
    0.40
    (
    0.40
    sofar
    0.39
     („
    0.39
     –
    0.38
     way
    0.38
    <0x80>
    0.37
    Activations Density 0.020%

    No Known Activations