© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7445
    Prev
    Next
    INDEX
    Explanations

    sentences that express that something is interesting

    oai_token-act-pair · gemini-2.0-flash

    interesting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    StoryboardSegue
    -0.82
     ivelany
    -0.76
     resourceCulture
    -0.73
     Roskov
    -0.73
    InvalidProtocol
    -0.71
     ModelExpression
    -0.69
    chieben
    -0.65
    :✨
    -0.62
    webElement
    -0.62
     esternos
    -0.60
    POSITIVE LOGITS
     interesting
    2.56
    interesting
    2.33
     Interesting
    2.16
    Interesting
    2.00
     INTEREST
    1.82
     interesante
    1.77
     interest
    1.73
     fascinating
    1.73
     интере
    1.68
     interessante
    1.68
    Activations Density 2.482%

    No Known Activations