© 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. 9234
    Prev
    Next
    INDEX
    Explanations

    place names, including town or district names

    oai_token-act-pair · gemini-2.0-flash

    technical terms or keywords in code/documentation

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

    place names

    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
     pié
    -0.49
    doj
    -0.46
     pé
    -0.46
    RTCK
    -0.46
    owano
    -0.44
    retrie
    -0.44
     lief
    -0.44
    öbb
    -0.44
    aget
    -0.43
     coupable
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.82
    PreferredItem
    0.78
    windowFixed
    0.76
     Exacts
    0.75
    numerusform
    0.73
    WithMany
    0.73
    tagHelperRunner
    0.73
    évaluateur
    0.71
    WebServlet
    0.71
     GenerationType
    0.71
    Activations Density 0.321%

    No Known Activations