© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1175
    Prev
    Next
    INDEX
    Explanations

    titles or awards given to people or books and the years given

    oai_token-act-pair · gemini-2.0-flash

    awards

    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
    تقاوى
    -0.98
    WithIOException
    -0.79
    Personensuche
    -0.77
     '\\;'
    -0.71
    aarrggbb
    -0.71
     vectorstock
    -0.69
     disponibilités
    -0.68
    UnknownFieldSet
    -0.67
    TintMode
    -0.67
     esternos
    -0.66
    POSITIVE LOGITS
     award
    2.02
     awards
    1.85
     Award
    1.80
    award
    1.70
    Award
    1.67
     Awards
    1.60
     AWARD
    1.55
    Awards
    1.52
    awards
    1.45
     awarded
    1.38
    Activations Density 1.091%

    No Known Activations