© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3692
    Prev
    Next
    INDEX
    Explanations

    the keyword "break" within code

    oai_token-act-pair · gemini-2.0-flash

    break

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    rawDesc
    -0.63
     jadx
    -0.56
    <?
    -0.51
    phorus
    -0.50
    mybatisplus
    -0.50
    NameInMap
    -0.50
    matchCondition
    -0.47
    ModelForm
    -0.47
    îtra
    -0.47
    ⓧ
    -0.47
    POSITIVE LOGITS
    OutputType
    0.54
    DrawerToggle
    0.53
     otomatig
    0.50
     doInBackground
    0.50
     mato
    0.48
     calendriers
    0.47
     Nye
    0.47
     AAS
    0.47
    })`
    0.46
    ApiModel
    0.46
    Activations Density 0.471%

    No Known Activations