© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2496
    Prev
    Next
    INDEX
    Explanations

    mentions of universities and degrees

    oai_token-act-pair · gemini-2.0-flash

    Universities/Education

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     tekem
    -0.41
     Fillmore
    -0.41
     ballo
    -0.40
    Aries
    -0.40
    ThroughAttribute
    -0.40
    >",
    -0.40
     Marlon
    -0.39
    примеча
    -0.39
     Jocelyn
    -0.39
     twit
    -0.39
    POSITIVE LOGITS
    #+#
    0.71
    Tikang
    0.69
    ARROLL
    0.68
     otomatig
    0.62
    WAII
    0.61
     كومونز
    0.60
    Personensuche
    0.60
    قایناق‌لار
    0.58
    ClientRect
    0.58
    Autoritní
    0.57
    Activations Density 3.781%

    No Known Activations