© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16258
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "cold" as used in temperatures or personality.

    oai_token-act-pair · gemini-2.0-flash

    cold

    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
     cold
    -3.11
    Cold
    -2.89
     Cold
    -2.89
    cold
    -2.84
     COLD
    -2.64
    COLD
    -2.38
     colder
    -1.95
     coldness
    -1.90
     chilly
    -1.82
     froid
    -1.80
    POSITIVE LOGITS
    Geplaatst
    0.70
    posedge
    0.58
    GraphicsUnit
    0.55
    encodeWith
    0.54
    enumi
    0.53
    \{\\
    0.52
     WARN
    0.50
    DoubleQuotes
    0.48
     Drapeau
    0.48
     referenties
    0.47
    Activations Density 3.335%

    No Known Activations