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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4092
    Prev
    Next
    INDEX
    Explanations

    the two-letter sequence "Ke" at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    Ke

    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
    a
    -0.54
    ye
    -0.52
    LayoutPanel
    -0.52
    bbene
    -0.52
    y
    -0.51
    ah
    -0.50
    aren
    -0.50
    yyy
    -0.49
    ctic
    -0.47
    yyyy
    -0.47
    POSITIVE LOGITS
    openqa
    0.54
    gus
    0.54
    Przypisy
    0.53
    gers
    0.49
    guo
    0.49
    OGND
    0.49
    tek
    0.49
    glu
    0.49
    ggg
    0.48
    gil
    0.48
    Activations Density 0.369%

    No Known Activations