© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10336
    Prev
    Next
    INDEX
    Explanations

    place names and prepositions

    oai_token-act-pair · gemini-2.0-flash

    British places and history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Referanser
    -0.50
    RetentionPolicy
    -0.45
    JsonKey
    -0.45
    QApplication
    -0.45
     dc
    -0.44
    interopRequire
    -0.44
    calipsis
    -0.43
     удовольствием
    -0.42
     insec
    -0.42
    הערות
    -0.42
    POSITIVE LOGITS
    SharedCtor
    0.77
    findpost
    0.69
     scolaires
    0.63
    rsiniz
    0.62
     fallu
    0.61
     againſt
    0.60
     BoxFit
    0.60
     насељу
    0.60
     judiciaire
    0.59
    )";
    0.58
    Activations Density 0.712%

    No Known Activations