© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12426
    Prev
    Next
    INDEX
    Explanations

    disclaimers in legal or consumer documents

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ValueStyle
    -0.80
    abestanden
    -0.77
     CreateTagHelper
    -0.77
    IntoConstraints
    -0.74
    Geplaatst
    -0.73
    PerformLayout
    -0.72
    +#+#
    -0.69
     TextAlign
    -0.68
    IsMutable
    -0.68
     surla
    -0.68
    POSITIVE LOGITS
    reicher
    0.47
    unay
    0.43
    topbar
    0.41
    gehenden
    0.41
     frames
    0.40
     '?'
    0.40
    RICS
    0.40
    ngdoc
    0.39
     refractory
    0.39
    etra
    0.39
    Activations Density 1.112%

    No Known Activations