© 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. 10545
    Prev
    Next
    INDEX
    Explanations

    text about training and competence

    oai_token-act-pair · gemini-2.0-flash

    training

    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
     training
    -3.06
    Training
    -2.81
     Training
    -2.81
    training
    -2.72
     TRAINING
    -2.63
     trained
    -2.52
    TRAINING
    -2.44
     Trained
    -2.22
    trained
    -2.16
    Trained
    -2.14
    POSITIVE LOGITS
    +#+#
    0.68
    interopRequire
    0.60
     Roskov
    0.56
    ::$_
    0.56
     entanto
    0.56
     resourceCulture
    0.56
     ویکی‌پدیا
    0.55
     jLabel
    0.54
    esModule
    0.54
    iastes
    0.53
    Activations Density 1.714%

    No Known Activations