© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12138
    Prev
    Next
    INDEX
    Explanations

    mentions of improvements and related terms

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "improvement"

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

    improvements

    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
     Numerade
    -0.88
    InitVars
    -0.78
    AccessorTable
    -0.76
    >);
    -0.75
    skjaer
    -0.75
     Theſe
    -0.74
    %");
    -0.74
    ])));
    -0.73
    }\]
    -0.73
     ―――――
    -0.72
    POSITIVE LOGITS
     possíveis
    0.48
     possible
    0.47
     posibles
    0.46
    possible
    0.46
     to
    0.46
    Possible
    0.46
     against
    0.45
    fjspx
    0.42
    ["
    0.41
     Possible
    0.40
    Activations Density 7.637%

    No Known Activations