© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4541
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "he" with surrounding context.

    oai_token-act-pair · gemini-2.0-flash

    He/She

    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
    SharedDtor
    -0.91
     thoſe
    -0.81
     theſe
    -0.79
    RenderAtEndOf
    -0.79
     thofe
    -0.75
     his
    -0.74
     thefe
    -0.73
     myſelf
    -0.72
     themſelves
    -0.71
     becauſe
    -0.69
    POSITIVE LOGITS
    ’
    0.75
    '
    0.68
    Revenir
    0.47
    isse
    0.46
    uk
    0.45
    pp
    0.44
    ena
    0.44
    irs
    0.44
    ili
    0.43
    zusch
    0.43
    Activations Density 4.573%

    No Known Activations