© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7629
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to inventions, technologies, and patents

    oai_token-act-pair · gemini-2.0-flash

    equipment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RenderAtEndOf
    -0.57
    Composable
    -0.50
    contentLoaded
    -0.48
     equipped
    -0.44
     adapted
    -0.44
     باخ
    -0.44
     EconPapers
    -0.43
    twimg
    -0.43
    帖最后由
    -0.43
     childs
    -0.42
    POSITIVE LOGITS
    iettivo
    0.68
    fastjson
    0.65
    SerializedName
    0.63
    ContentAlignment
    0.62
    дә
    0.58
    LLocation
    0.57
    icolon
    0.56
     Waray
    0.56
    łbym
    0.55
    interopRequire
    0.54
    Activations Density 18.245%

    No Known Activations