© 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
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1703
    Prev
    Next
    INDEX
    Explanations

    HTML related tags

    oai_token-act-pair · gemini-2.0-flash

    equiv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    PreferredItem
    -0.62
    rungsseite
    -0.61
    igshid
    -0.57
    dotenv
    -0.54
     Roskov
    -0.53
    withIdentifier
    -0.52
    lando
    -0.50
    oneg
    -0.49
    NewUrlParser
    -0.49
    DebuggerNonUser
    -0.49
    POSITIVE LOGITS
     jsPsych
    0.63
     Gegenteil
    0.54
     déploy
    0.52
    rrggbb
    0.51
    ității
    0.48
    cknow
    0.47
    ulada
    0.47
     tille
    0.47
     Rektor
    0.46
    arakhand
    0.46
    Activations Density 2.080%

    No Known Activations