© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12774
    Prev
    Next
    INDEX
    Explanations

    words that appear to be associated with data-organization, names, acronyms and scientific categories

    oai_token-act-pair · gemini-2.0-flash

    describing aspects/features

    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
    same
    -0.61
     Same
    -0.59
     same
    -0.57
    Same
    -0.56
     dieselbe
    -0.53
     derselbe
    -0.52
    })*/
    -0.52
     alike
    -0.51
     للاسماء
    -0.51
    resultCode
    -0.50
    POSITIVE LOGITS
    writeFieldEnd
    0.65
    enfone
    0.63
    indale
    0.52
    
    0.48
    SpringBootTest
    0.47
     laterale
    0.47
     Gable
    0.46
    AutoScaleMode
    0.46
     Mě
    0.46
     Gegenteil
    0.45
    Activations Density 5.809%

    No Known Activations