© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258319
    Prev
    Next
    INDEX
    Explanations

    emoticons and laughter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    -
    0.68
    _
    0.56
    z
    0.54
    all
    0.51
    back
    0.43
    c
    0.42
    lo
    0.42
    ku
    0.41
    Acid
    0.41
    burg
    0.41
    POSITIVE LOGITS
     전략
    0.56
     우선
    0.55
    <unused1097>
    0.55
     interferometer
    0.53
     estratégia
    0.53
    分辨率
    0.52
     DirectX
    0.52
     stratégie
    0.52
    手指
    0.52
     chatbots
    0.51
    Activations Density 0.001%

    No Known Activations