© 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. 8599
    Prev
    Next
    INDEX
    Explanations

    scientific language about systems changing states

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'start'

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

    starting

    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
    ɵɵ
    -0.50
    脚注の使い方
    -0.50
    ConstraintMaker
    -0.48
    PCell
    -0.47
    AndEndTag
    -0.47
     colorWith
    -0.46
    useNewUrlParser
    -0.45
    क्षित
    -0.44
    AddressBook
    -0.43
     BorderLayout
    -0.43
    POSITIVE LOGITS
     starting
    2.81
     Starting
    2.56
     start
    2.55
    starting
    2.52
    Starting
    2.52
     starts
    2.47
     Start
    2.28
     Starts
    2.27
    start
    2.25
     started
    2.23
    Activations Density 4.335%

    No Known Activations