© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6687
    Prev
    Next
    INDEX
    Explanations

    java code blocks delimited by parentheses and curly braces, or javascript testing code blocks

    oai_token-act-pair · gemini-2.0-flash

    });

    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
    .
    -0.53
    quently
    -0.46
    plained
    -0.45
    LEVANT
    -0.45
    مرت
    -0.45
     Bas
    -0.44
     Lag
    -0.44
     Gordon
    -0.43
     Baz
    -0.43
    ).
    -0.42
    POSITIVE LOGITS
     ་་
    0.90
    featureID
    0.87
    WebVitals
    0.84
     Cæsar
    0.83
    )";
    0.82
     $_"
    0.82
    +')
    0.81
    >");
    0.80
    };*/
    0.77
    Tikang
    0.77
    Activations Density 1.440%

    No Known Activations