© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15097
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fire" in the context of fire fighting

    oai_token-act-pair · gemini-2.0-flash

    light

    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
    SequentialGroup
    -0.56
     ExecuteAsync
    -0.51
    Geplaatst
    -0.49
    balan
    -0.46
     launches
    -0.45
     uitgenodigd
    -0.43
     introductions
    -0.43
     digress
    -0.43
     Arte
    -0.42
     wieś
    -0.41
    POSITIVE LOGITS
     lit
    1.63
     lighting
    1.55
    Lighting
    1.39
    lighting
    1.38
     Lighting
    1.38
    lit
    1.27
     lights
    1.20
     lighted
    1.20
    LIGHTING
    1.10
    lights
    1.09
    Activations Density 3.760%

    No Known Activations