© 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. 3658
    Prev
    Next
    INDEX
    Explanations

    phrases used in legal documents to support a finding or demonstrate compliance with a rule.

    oai_token-act-pair · gemini-2.0-flash

    observations

    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
    ிறது
    -0.53
    Xna
    -0.52
    बाह
    -0.51
    Captor
    -0.50
    LookAnd
    -0.50
    tement
    -0.50
    prilis
    -0.47
    addFlags
    -0.47
     ainfi
    -0.47
    луй
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.67
    liflower
    0.58
     समीक्षाओं
    0.57
    WebVitals
    0.56
     Winaray
    0.55
    arraycopy
    0.55
    ]")]
    0.52
     Songtext
    0.49
    SequentialGroup
    0.49
     Pinn
    0.49
    Activations Density 18.143%

    No Known Activations