© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11386
    Prev
    Next
    INDEX
    Explanations

    code from an application

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    tvguidetime
    -0.64
    +:+
    -0.60
     مشين
    -0.51
    tinyos
    -0.49
    sendRedirect
    -0.49
    <bos>
    -0.49
    !*\
    -0.49
     pedicure
    -0.49
    medades
    -0.49
    неопр
    -0.48
    POSITIVE LOGITS
    OGND
    0.60
     Италијани
    0.55
     OFDb
    0.50
    يكب
    0.48
    Демографія
    0.46
    TestBed
    0.44
    thâu
    0.43
     transfieras
    0.43
    intios
    0.42
    CharStream
    0.40
    Activations Density 4.273%

    No Known Activations