© 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. 5451
    Prev
    Next
    INDEX
    Explanations

    text formatting and structure in a document, such as newlines, titles, and separators

    oai_token-act-pair · gemini-2.0-flash

    Unstructured or mixed data

    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
     itſelf
    -0.65
     raiſ
    -0.64
     myſelf
    -0.60
     becauſe
    -0.51
     Efq
    -0.51
    leſs
    -0.50
    TagMode
    -0.50
    verständlich
    -0.49
     uſed
    -0.49
    OGND
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.68
     Make
    0.65
     Making
    0.61
    abstractmethod
    0.60
     Berman
    0.59
     JADX
    0.59
    Make
    0.59
    Making
    0.56
     MAKING
    0.56
    heira
    0.56
    Activations Density 43.815%

    No Known Activations