© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6177
    Prev
    Next
    INDEX
    Explanations

    phrases involving comparisons, obtaining something, and relationships between entities

    oai_token-act-pair · gemini-2.0-flash

    say "one"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ones
    -2.41
     Ones
    -2.14
    ones
    -1.93
    Ones
    -1.84
    One
    -1.25
     One
    -1.23
    ONE
    -1.18
    ONES
    -1.16
    one
    -1.16
     ONE
    -1.13
    POSITIVE LOGITS
    rungsseite
    1.28
     '\\;'
    1.23
    windowFixed
    1.22
    GEBURTSDATUM
    1.21
    ########.
    1.20
     समीक्षाओं
    1.16
     ProtoMessage
    1.11
    RenderAtEndOf
    1.08
    تقاوى
    1.07
     himo
    1.06
    Activations Density 0.811%

    No Known Activations