© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9337
    Prev
    Next
    INDEX
    Explanations

    text that is enthusiastic or positive, often using intensifiers like "really" and exclamation points.

    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
     wonderful
    -0.94
     marvelous
    -0.90
     marvellous
    -0.89
    wonderful
    -0.88
     Interesting
    -0.84
    Interesting
    -0.83
    interesting
    -0.82
     interesting
    -0.82
     fantastic
    -0.81
    Wonderful
    -0.80
    POSITIVE LOGITS
     cool
    2.34
    cool
    2.16
     Cool
    2.06
    Cool
    2.05
     COOL
    1.85
     coolness
    1.70
    COOL
    1.64
     coolest
    1.63
     cooler
    1.53
     cools
    1.38
    Activations Density 8.088%

    No Known Activations