© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9446
    Prev
    Next
    INDEX
    Explanations

    the prefix 'pro'

    oai_token-act-pair · gemini-2.0-flash

    tokens related to programming or code constructs

    np_token-act-pair-logits · gpt-4o-mini

    pro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     مواليد
    -0.47
    Debido
    -0.47
    setMaximum
    -0.45
     Feeling
    -0.43
    płat
    -0.42
    jut
    -0.42
    missione
    -0.42
    upassen
    -0.42
     élector
    -0.41
    GraphicsUnit
    -0.41
    POSITIVE LOGITS
    +#+#
    0.71
    Autoritní
    0.60
    HasForeignKey
    0.57
    protoimpl
    0.56
     Majefty
    0.55
     pleaſure
    0.55
    ymce
    0.53
    writeField
    0.52
    ChildScrollView
    0.52
    外部リンク
    0.52
    Activations Density 0.115%

    No Known Activations