© 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. 1456
    Prev
    Next
    INDEX
    Explanations

    noun phrases describing the properties of different materials

    oai_token-act-pair · gemini-2.0-flash

    Technical descriptions

    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
     ModelExpression
    -0.76
     betweenstory
    -0.75
    parsedMessage
    -0.75
    SourceChecksum
    -0.71
    ImageContext
    -0.69
    OGND
    -0.69
    adaptiveStyles
    -0.69
     typelib
    -0.68
     Vikipedi
    -0.68
     présentés
    -0.68
    POSITIVE LOGITS
     group
    0.74
    Group
    0.62
    group
    0.60
     Group
    0.60
    .
    0.51
     GROUP
    0.50
    GROUP
    0.50
     groups
    0.49
    groups
    0.48
     reference
    0.48
    Activations Density 4.225%

    No Known Activations