© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12822
    Prev
    Next
    INDEX
    Explanations

    the word "kinds" and words meaning "truly"

    oai_token-act-pair · gemini-2.0-flash

    kinds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     esophagus
    -0.62
     civilizations
    -0.55
     theaters
    -0.54
     celular
    -0.52
     harbors
    -0.51
     Coh
    -0.50
    jbl
    -0.50
     Cessna
    -0.50
     gasoline
    -0.49
    ja
    -0.49
    POSITIVE LOGITS
    adaptiveStyles
    0.95
     مرئيه
    0.92
    bootstrapcdn
    0.89
     defaultstate
    0.89
     EconPapers
    0.83
    TypedDataSet
    0.83
    SequentialGroup
    0.82
     تضيفلها
    0.81
     BoxFit
    0.80
    rungsseite
    0.78
    Activations Density 0.603%

    No Known Activations