© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5477
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss something's importance, existence, or reality using auxiliary verbs and related language

    oai_token-act-pair · gemini-2.0-flash

    forms of "to be"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    parsedMessage
    -0.77
    帖最后由
    -0.77
    tvguidetime
    -0.76
    rungsseite
    -0.73
     ModelExpression
    -0.72
     estimés
    -0.70
     propOrder
    -0.68
    webElementXpaths
    -0.68
     AssemblyCulture
    -0.67
     otomatig
    -0.67
    POSITIVE LOGITS
     real
    0.59
     most
    0.47
     Most
    0.46
    real
    0.45
    ễn
    0.44
    шта
    0.42
     Real
    0.42
     kezd
    0.42
     Am
    0.42
     Ne
    0.40
    Activations Density 3.470%

    No Known Activations