© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3744
    Prev
    Next
    INDEX
    Explanations

    articles and adjectives

    oai_token-act-pair · gemini-2.0-flash

    person

    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
     men
    -0.84
     friends
    -0.75
     women
    -0.65
     friend
    -0.62
    men
    -0.59
    friends
    -0.57
     Men
    -0.57
     Friend
    -0.56
    friend
    -0.56
     distanciation
    -0.54
    POSITIVE LOGITS
    ValueGenerated
    0.61
    SharedDtor
    0.60
     okuyayım
    0.56
     <=",
    0.56
    Activités
    0.51
    ilibrium
    0.51
     diamants
    0.51
     administracy
    0.50
     tarto
    0.50
     capitolo
    0.50
    Activations Density 5.205%

    No Known Activations