© 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. 4472
    Prev
    Next
    INDEX
    Explanations

    double quotes with a space after them in code

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    ERAL
    -0.54
    aris
    -0.51
     géné
    -0.49
    dika
    -0.45
    okia
    -0.45
    থা
    -0.44
     and
    -0.44
    isse
    -0.44
    arms
    -0.44
    setModel
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.80
    Enllaces
    0.75
     utafitiHapana
    0.73
     StatelessWidget
    0.71
    SequentialGroup
    0.70
    RegressionTest
    0.69
    TagMode
    0.65
    #+#
    0.65
     חיצוניים
    0.64
    MessageOf
    0.64
    Activations Density 0.776%

    No Known Activations