© 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. 10713
    Prev
    Next
    INDEX
    Explanations

    a word or phrase that is included in multiple medical/scientific publications

    oai_token-act-pair · gemini-2.0-flash

    statements of fact

    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
    })));
    -0.65
    ябре
    -0.63
    ]));
    -0.59
     vuitton
    -0.59
    RuleContext
    -0.59
    dafx
    -0.58
    phrine
    -0.57
    fjspx
    -0.57
    phazard
    -0.57
    vitational
    -0.56
    POSITIVE LOGITS
    VersionUID
    0.57
     escenarios
    0.54
     quæ
    0.50
     rerum
    0.49
     culturelles
    0.48
    delli
    0.48
    باح
    0.47
    XmlRootElement
    0.47
     above
    0.46
     superiori
    0.46
    Activations Density 3.779%

    No Known Activations