© 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. 2309
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to purpose, goals, or objectives.

    oai_token-act-pair · gemini-2.0-flash

    aims

    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
    TemporalType
    -0.53
     समीक्षक
    -0.49
    __*/
    -0.47
     esternos
    -0.47
    الدراسه
    -0.46
    webElement
    -0.43
    DockStyle
    -0.43
    ViewStyle
    -0.42
     BorderSide
    -0.42
     étrang
    -0.42
    POSITIVE LOGITS
    <bos>
    0.79
    出版年
    0.64
    uxxxx
    0.52
    #+#
    0.50
     Milo
    0.49
     MyBatis
    0.49
     tufted
    0.49
    taines
    0.49
    IsContent
    0.49
    Попис
    0.48
    Activations Density 4.791%

    No Known Activations