© 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. 4687
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by another word.

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    IsContent
    -0.78
     ujednoznacz
    -0.75
    ⓧ
    -0.73
     CreateTagHelper
    -0.72
     виправивши
    -0.71
    httphttps
    -0.71
     فريبيس
    -0.70
    thâu
    -0.69
    complexContent
    -0.68
     consultato
    -0.67
    POSITIVE LOGITS
    randrange
    0.45
    PRNewswire
    0.45
    IFIER
    0.45
    IRIT
    0.44
    atten
    0.40
    ittà
    0.39
    view
    0.38
    рана
    0.38
     ++)
    0.38
    항
    0.38
    Activations Density 2.125%

    No Known Activations