Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9851
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to purchasing items, particularly technology and vehicles

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
     enmity
    -0.61
     crimin
    -0.61
     Murder
    -0.60
     morphe
    -0.60
     repentance
    -0.59
     schizophrenia
    -0.59
     ritu
    -0.58
     despotism
    -0.57
     absurdity
    -0.57
     arithmetic
    -0.57
    POSITIVE LOGITS
     hemsida
    0.47
     doccia
    0.47
     américains
    0.44
     zubehör
    0.43
     alluminio
    0.42
     fahrrad
    0.42
    vägen
    0.42
     todėl
    0.42
     edelstahl
    0.42
     webbplats
    0.41
    Activations Density 37.368%

    No Known Activations