© 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. 9709
    Prev
    Next
    INDEX
    Explanations

    instances of people or objects being located "on" something, especially when lying or sitting.

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "top"

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

    on

    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
    Personendaten
    -0.94
    KURZBESCHREIBUNG
    -0.93
     betweenstory
    -0.90
     onOptions
    -0.84
     defStyleAttr
    -0.84
    ArgsConstructor
    -0.83
     createContext
    -0.82
     FetchType
    -0.81
     المعيارى
    -0.80
    KommentareTeilen
    -0.78
    POSITIVE LOGITS
     top
    0.93
    top
    0.77
     the
    0.68
    Top
    0.57
     Top
    0.52
     Spitze
    0.44
    トップ
    0.44
     tops
    0.43
     शीर्ष
    0.43
     اول
    0.42
    Activations Density 0.804%

    No Known Activations