© 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-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14492
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to exposure of the human body or medical inspection.

    oai_token-act-pair · gemini-2.0-flash

    naked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     läßt
    -0.74
     pageNo
    -0.73
     itſelf
    -0.70
     Efq
    -0.69
     pelbagai
    -0.69
     ſhe
    -0.68
     scania
    -0.68
     morire
    -0.68
     seru
    -0.68
     biß
    -0.67
    POSITIVE LOGITS
    ’
    0.64
    MethodManager
    0.62
     bellow
    0.61
     in
    0.61
    ️
    0.60
     
    0.60
    ourced
    0.59
    ticides
    0.57
    phed
    0.56
    erol
    0.55
    Activations Density 3.318%

    No Known Activations