© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13381
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words 'android', 'ios', 'mouth', or 'face'

    oai_token-act-pair · gemini-2.0-flash

    android

    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
    Negative Logits
     BehaviorSubject
    -0.65
    ل
    -0.65
    assin
    -0.64
     StatelessWidget
    -0.60
     preuves
    -0.60
    בור
    -0.59
    NgModule
    -0.59
    حياته
    -0.59
    atola
    -0.58
     stringBuilder
    -0.57
    POSITIVE LOGITS
     ProtoMessage
    0.70
     Chwiliwch
    0.64
    StructEnd
    0.63
    FunctionFlags
    0.62
    InputBorder
    0.59
    +#+
    0.58
    potranspiration
    0.57
    <bos>
    0.57
     dAtA
    0.56
     ComVisible
    0.56
    Activations Density 1.382%

    No Known Activations