© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3162
    Prev
    Next
    INDEX
    Explanations

    proper nouns and terms of finance or legality

    oai_token-act-pair · gemini-2.0-flash

    terms related to legal and patent topics

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

    Legal and political topics

    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
     suivants
    -0.78
     seguenti
    -0.70
     quæ
    -0.69
     suivante
    -0.68
     normaux
    -0.68
     seguente
    -0.68
     zelve
    -0.66
     démocr
    -0.66
     réguli
    -0.66
     dépass
    -0.66
    POSITIVE LOGITS
     band
    0.75
     climate
    0.68
     experiment
    0.68
     landscape
    0.66
     prototype
    0.66
     security
    0.66
     course
    0.65
     conference
    0.65
     children
    0.65
     hom
    0.65
    Activations Density 7.765%

    No Known Activations