© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13234
    Prev
    Next
    INDEX
    Explanations

    capitalized letters followed by periods, especially those indicating academic degrees

    oai_token-act-pair · gemini-2.0-flash

    academic degrees/certifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    parsedMessage
    -0.68
     Италијани
    -0.65
    SourceChecksum
    -0.65
    oredCriteria
    -0.64
    expandindo
    -0.64
     "}";
    -0.61
     незавершена
    -0.58
     pinulongan
    -0.58
     **)
    -0.55
    IVEREF
    -0.55
    POSITIVE LOGITS
    ACHI
    0.53
     eccl
    0.46
    벌
    0.45
     Hins
    0.44
    useState
    0.43
    TimeUnit
    0.43
    Forms
    0.43
    tember
    0.42
    guisement
    0.42
    RunWith
    0.42
    Activations Density 1.840%

    No Known Activations