© 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. 12728
    Prev
    Next
    INDEX
    Explanations

    the letter "A" followed by another letter or number, especially when the "A" is part of an abbreviation

    oai_token-act-pair · gemini-2.0-flash

    patterns starting with 'A'

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

    A

    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
    adaptiveStyles
    -0.63
    quilo
    -0.59
     onItemClick
    -0.58
     auger
    -0.57
     emballage
    -0.57
    adpleegd
    -0.56
     odour
    -0.55
    principalColumn
    -0.54
    FontOfSize
    -0.54
    Jeografia
    -0.54
    POSITIVE LOGITS
    ash
    0.56
    il
    0.55
    oc
    0.52
    ap
    0.52
    ag
    0.52
    oto
    0.51
    WebControls
    0.51
    ol
    0.50
    ay
    0.49
    am
    0.49
    Activations Density 1.476%

    No Known Activations