© 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. 12643
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Dan" with surrounding context

    oai_token-act-pair · gemini-2.0-flash

    non-standard or malformed inputs

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

    fictional media

    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
     bezoek
    -0.57
     douleurs
    -0.47
    TypedDataSet
    -0.46
    intéress
    -0.44
     pouvoirs
    -0.43
    guera
    -0.41
     poussière
    -0.40
    قایناقلار
    -0.39
     stør
    -0.39
     récentes
    -0.39
    POSITIVE LOGITS
    aarrggbb
    0.75
     Himo
    0.71
    wapV
    0.69
    Geplaatst
    0.68
     Lyman
    0.63
     BorderRadius
    0.62
     hit
    0.61
     actionMode
    0.61
     Reverso
    0.60
     InputDecoration
    0.60
    Activations Density 0.331%

    No Known Activations