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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10294
    Prev
    Next
    INDEX
    Explanations

    internet URLs and related terms (follow, channel, etc.) followed by social media platform names (Twitter, Instagram)

    oai_token-act-pair · gemini-2.0-flash

    !

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ialog
    -0.47
     The
    -0.46
    n
    -0.45
    genstein
    -0.42
    unes
    -0.41
     Autónoma
    -0.40
    ’
    -0.40
    tures
    -0.40
    ssil
    -0.40
    LLES
    -0.40
    POSITIVE LOGITS
    saraba
    0.71
     ModelExpression
    0.70
    :✨
    0.67
    ="#"><
    0.66
    ymce
    0.65
     pinulongan
    0.64
    AddHtmlAttribute
    0.63
     BoxDecoration
    0.63
     Administrativna
    0.60
    KommentareTeilen
    0.57
    Activations Density 13.572%

    No Known Activations