© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14162
    Prev
    Next
    INDEX
    Explanations

    words relating to hiking in a desert climate

    oai_token-act-pair · gemini-2.0-flash

    heat

    np_max-act-logits · gemini-2.0-flash

    say "summer/heat" Method used: 2 — tokens after activation indicate summer/heat, so say "summer/heat"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Cool
    -0.96
    Cool
    -0.95
     chill
    -0.92
     coolness
    -0.92
     cold
    -0.92
     cool
    -0.91
     cooling
    -0.91
     chilled
    -0.91
     COOL
    -0.89
     Chill
    -0.88
    POSITIVE LOGITS
     hot
    2.17
     Hot
    1.87
    Hot
    1.85
    hot
    1.84
     HOT
    1.73
     heat
    1.64
    HOT
    1.64
     hotter
    1.52
     Heat
    1.48
    heat
    1.47
    Activations Density 2.191%

    No Known Activations