© 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. 13959
    Prev
    Next
    INDEX
    Explanations

    conditionals with "if" and related words such as "you"

    oai_token-act-pair · gemini-2.0-flash

    If

    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
    Atentamente
    -0.68
    surate
    -0.64
    "]);
    -0.63
     />";
    -0.63
    astéroïdes
    -0.62
    ]";
    -0.61
    '));
    -0.61
    }';
    -0.59
    });*/
    -0.58
    }`).
    -0.58
    POSITIVE LOGITS
     ModelExpression
    0.75
    BeginInit
    0.61
     financially
    0.51
    openqa
    0.50
     fishing
    0.48
     financial
    0.47
     reading
    0.47
    myn
    0.47
     ویکی‌پدیا
    0.46
    ​
    0.46
    Activations Density 0.813%

    No Known Activations