© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5280
    Prev
    Next
    INDEX
    Explanations

    the word "You're" followed by positive affirmation or some form of directional language

    oai_token-act-pair · gemini-2.0-flash

    answering a question

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    GEBURTSDATUM
    -0.98
     дописавши
    -0.83
    HtmlAttribute
    -0.75
     propOrder
    -0.75
    IsContent
    -0.73
     tartalomajánló
    -0.73
     ويكيميديا
    -0.71
    脚注の使い方
    -0.69
    Hentet
    -0.68
    RenderAtEndOf
    -0.67
    POSITIVE LOGITS
     your
    0.49
     alive
    0.48
     success
    0.46
     nim
    0.43
    your
    0.43
    ngOn
    0.42
     Ejecutivo
    0.41
     Ст
    0.41
     not
    0.41
     in
    0.40
    Activations Density 0.631%

    No Known Activations