© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14426
    Prev
    Next
    INDEX
    Explanations

    HTML tags and URLs found in source code

    oai_token-act-pair · gemini-2.0-flash

    Web links and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Monfieur
    -0.65
     Efq
    -0.63
     Houſe
    -0.57
     houſe
    -0.55
     becauſe
    -0.53
     Majefty
    -0.53
     Reſ
    -0.52
     againſt
    -0.52
     purpoſe
    -0.51
     ſtre
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
    findpost
    0.64
    twimg
    0.62
    __))
    0.62
    %",
    0.61
    -
    0.60
    +),
    0.60
    featureID
    0.59
    ‑
    0.59
    %，
    0.58
    Activations Density 16.176%

    No Known Activations