© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7867
    Prev
    Next
    INDEX
    Explanations

    the word "soul" and words related to shopping or retail

    oai_token-act-pair · gemini-2.0-flash

    soul or shopping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ing
    -0.61
    amaño
    -0.60
     afic
    -0.58
     مقاب
    -0.57
    acheteur
    -0.56
    ividual
    -0.56
    momix
    -0.55
    weise
    -0.55
     indeed
    -0.54
    Samstag
    -0.54
    POSITIVE LOGITS
     vectorielles
    1.02
     fermés
    0.94
     enfans
    0.90
     feroit
    0.88
     avoient
    0.87
     étoient
    0.82
     étoit
    0.82
     supérieures
    0.82
     nakalista
    0.81
    #
    0.79
    Activations Density 1.694%

    No Known Activations