© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 10155
    Prev
    Next
    INDEX
    Explanations

    words related to physical sensations and experiences, sometimes with a sexual context

    oai_token-act-pair · gemini-2.0-flash

    Encoding errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    aronder
    -0.57
    enskap
    -0.57
    rensa
    -0.52
    ConstraintMaker
    -0.50
     الحره
    -0.50
    /−
    -0.49
    PickerController
    -0.47
    pley
    -0.47
    ariato
    -0.47
    ôle
    -0.47
    POSITIVE LOGITS
    WithIOException
    0.65
    AutoScaleMode
    0.59
    İstinadlar
    0.56
    évaluateur
    0.55
    存于互联网档案馆
    0.55
    ьаж
    0.54
     correctes
    0.54
     moeda
    0.53
    verifyException
    0.52
    yaszt
    0.50
    Activations Density 5.014%

    No Known Activations