© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12806
    Prev
    Next
    INDEX
    Explanations

    mentions of ethnicities and groups of people

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax or keywords

    np_token-act-pair-logits · gpt-4o-mini

    Ethnic groups and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    EDEFAULT
    -0.66
     AssemblyProduct
    -0.58
     AssemblyTitle
    -0.57
    himp
    -0.53
    OGND
    -0.48
    Demografía
    -0.45
     وصلة
    -0.45
     getApplication
    -0.45
     snippetHide
    -0.44
     plaît
    -0.44
    POSITIVE LOGITS
    })*/
    0.66
     GreatSchools
    0.58
    ("]");
    0.53
    Filmographie
    0.53
    });*/
    0.52
     skóra
    0.52
    peza
    0.52
     betweenstory
    0.52
    ScopeManager
    0.51
    vernote
    0.50
    Activations Density 3.031%

    No Known Activations