© 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. 2011
    Prev
    Next
    INDEX
    Explanations

    descriptions of people, including their nationality, occupation, or connection to a sporting event

    oai_token-act-pair · gemini-2.0-flash

    Biographies of people

    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
     Roskov
    -0.86
    AccessorTable
    -0.84
     invokingState
    -0.79
    TagMode
    -0.78
    +:+
    -0.77
     виправивши
    -0.75
     estekak
    -0.69
    RenderAtEndOf
    -0.66
     betweenstory
    -0.66
    SequentialGroup
    -0.63
    POSITIVE LOGITS
    litz
    0.49
    saraba
    0.46
    øde
    0.45
    россий
    0.44
    monary
    0.43
    vede
    0.41
    libft
    0.40
    randrange
    0.40
     ground
    0.39
     nacidos
    0.39
    Activations Density 1.152%

    No Known Activations