© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15136
    Prev
    Next
    INDEX
    Explanations

    references to government and legislative policy

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     argparse
    -0.56
    vnd
    -0.48
    apimachinery
    -0.46
     fichiers
    -0.43
    mybatisplus
    -0.43
    出版年
    -0.43
     azok
    -0.43
    NewUrlParser
    -0.43
    공
    -0.42
     parteci
    -0.42
    POSITIVE LOGITS
     passage
    0.65
    ViewFeatures
    0.63
     Crusoe
    0.60
    DoubleQuotes
    0.59
    >*/
    0.57
    StructEnd
    0.57
     TestBed
    0.56
     omnibus
    0.56
    phazard
    0.54
    zmir
    0.54
    Activations Density 1.756%

    No Known Activations