© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9291
    Prev
    Next
    INDEX
    Explanations

    code snippets utilizing terms such as "instance", "ports", "multi", "Request", and "msg".

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.56
    enumi
    -0.43
    misu
    -0.42
     но
    -0.41
    inaudible
    -0.39
    پر
    -0.39
    chal
    -0.39
     PeEnEo
    -0.39
     but
    -0.38
    mot
    -0.38
    POSITIVE LOGITS
     disambiguazione
    0.57
    Tikang
    0.54
     judicious
    0.50
    ⓧ
    0.50
    IsMutable
    0.49
    SuppressMessage
    0.49
    LayoutPanel
    0.48
    ThroughAttribute
    0.47
    XmlType
    0.46
     útil
    0.45
    Activations Density 2.264%

    No Known Activations