© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11258
    Prev
    Next
    INDEX
    Explanations

    hyphens in what appear to be document IDs

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    GEBURTSDATUM
    -0.80
    livia
    -0.69
    uesday
    -0.59
     يتيمه
    -0.59
     gyhoeddwyd
    -0.57
     незавершена
    -0.56
    __*/
    -0.56
    utterstock
    -0.54
    contentLoaded
    -0.54
    america
    -0.53
    POSITIVE LOGITS
     referrerpolicy
    0.53
    yelidikan
    0.50
    ValueStyle
    0.49
     Himo
    0.47
     ngang
    0.46
    ReusableCell
    0.46
    mappedBy
    0.42
    Попис
    0.42
     bandeja
    0.42
    Xar
    0.41
    Activations Density 0.410%

    No Known Activations