© 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. 4146
    Prev
    Next
    INDEX
    Explanations

    the phrase "a bit" and similar phrases that describe something minor

    oai_token-act-pair · gemini-2.0-flash

    Subjective opinions

    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
     ویکی‌پدیای
    -0.65
     fieldNum
    -0.65
    Personensuche
    -0.65
    seamnă
    -0.64
     transférez
    -0.61
    GEBURTS
    -0.60
     Италијани
    -0.60
     verdaderas
    -0.60
    AutoresizingMask
    -0.60
     تكبرها
    -0.60
    POSITIVE LOGITS
     much
    0.48
    ๆ
    0.44
     of
    0.42
    DoubleQuotes
    0.41
    kane
    0.39
    omer
    0.39
     sceptical
    0.39
     scepticism
    0.38
     gentler
    0.38
    ره
    0.37
    Activations Density 2.118%

    No Known Activations