© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13766
    Prev
    Next
    INDEX
    Explanations

    words that express a degree of complexity, time passing, and an action is underway

    oai_token-act-pair · gemini-2.0-flash

    complexity

    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
    <bos>
    -0.72
     Paglinawan
    -0.52
    '];?>
    -0.52
    '])->
    -0.50
    "):
    -0.48
    koo
    -0.46
     Kemp
    -0.46
    '''
    -0.44
    ()));
    -0.44
    LookAnd
    -0.44
    POSITIVE LOGITS
    ⓧ
    0.59
    Gön
    0.57
    Obrázky
    0.56
     NSCoder
    0.49
    AndEndTag
    0.48
    ArgsConstructor
    0.47
    XmlAccessorType
    0.47
    IonicModule
    0.47
     للمعارف
    0.46
    udesta
    0.46
    Activations Density 0.690%

    No Known Activations