© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14739
    Prev
    Next
    INDEX
    Explanations

    the word "Academy", particularly connected to names

    oai_token-act-pair · gemini-2.0-flash

    Academy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    '
    -0.56
     diz
    -0.47
    графи
    -0.46
    ụ
    -0.46
     of
    -0.45
     od
    -0.45
    rénées
    -0.44
     ch
    -0.44
    xea
    -0.44
     pom
    -0.43
    POSITIVE LOGITS
    >{@
    0.91
    cessite
    0.87
     désol
    0.86
     démocr
    0.85
     Monfieur
    0.84
     houſe
    0.83
     Majefty
    0.83
    ContentAsync
    0.82
    Hauptartikel
    0.80
     greateſt
    0.80
    Activations Density 0.667%

    No Known Activations