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. 9585
    Prev
    Next
    INDEX
    Explanations

    business oriented language and statistics from texts related to medicine

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    ViewFeatures
    -0.68
     deal
    -0.65
     Italijanski
    -0.63
     Deal
    -0.62
     ErrIntOverflow
    -0.61
    getMenuInflater
    -0.60
    Deal
    -0.59
     DEAL
    -0.59
    esModule
    -0.58
    eloma
    -0.57
    POSITIVE LOGITS
    Gegen
    0.43
     ويكيميديا
    0.43
    under
    0.42
    Blurb
    0.42
     under
    0.41
    Artículo
    0.41
    Under
    0.41
     <<<<<<<<<<<<<<
    0.40
    hydrates
    0.39
     vnder
    0.39
    Activations Density 6.150%

    No Known Activations