© 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. 4065
    Prev
    Next
    INDEX
    Explanations

    phrases describing someone's academic achievements and/or education

    oai_token-act-pair · gemini-2.0-flash

    educational qualifications

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

    educational degrees

    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
     للمعارف
    -0.66
     Theſe
    -0.62
     Houſe
    -0.59
    tvguidetime
    -0.58
    ContentAsync
    -0.55
     houſe
    -0.55
     Majefty
    -0.53
    новниш
    -0.52
     Diſ
    -0.52
     leaſt
    -0.51
    POSITIVE LOGITS
    ValueStyle
    0.53
     INSEE
    0.53
     AssemblyCulture
    0.51
     subido
    0.50
    warzys
    0.48
    emption
    0.45
     nõ
    0.44
    >";
    0.44
    bardier
    0.44
    getSeconds
    0.43
    Activations Density 0.946%

    No Known Activations