© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9992
    Prev
    Next
    INDEX
    Explanations

    java getter methods with parentheses

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     surla
    -0.72
    AsUp
    -0.66
    >>()
    -0.65
    })`
    -0.63
    tvguidetime
    -0.62
    ActionCreators
    -0.62
    }}/>
    -0.58
     rootReducer
    -0.57
    ]))
    -0.55
     DIB
    -0.55
    POSITIVE LOGITS
     تضيفلها
    0.69
    lawesi
    0.54
     يتيمه
    0.52
    didSet
    0.49
     CreateTagHelper
    0.48
     destrucción
    0.47
    windowFixed
    0.45
    SequentialGroup
    0.44
    sendMail
    0.44
    TacToe
    0.44
    Activations Density 5.112%

    No Known Activations