© 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. 9877
    Prev
    Next
    INDEX
    Explanations

    content having to do with air temperature, heat, and cooling

    oai_token-act-pair · gemini-2.0-flash

    cool

    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
    }`}>
    -0.66
    ForRow
    -0.65
    Personensuche
    -0.64
    VersionUID
    -0.63
    HostException
    -0.63
     createSprite
    -0.59
    AddTagHelper
    -0.59
    yntaxException
    -0.57
    />";
    -0.57
    ContentAlignment
    -0.56
    POSITIVE LOGITS
     cool
    2.55
    cool
    2.28
    Cool
    2.19
     Cool
    2.19
     coolest
    1.95
     COOL
    1.91
     coolness
    1.84
    COOL
    1.73
     cooler
    1.59
    cooler
    1.30
    Activations Density 5.997%

    No Known Activations