© 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. 5199
    Prev
    Next
    INDEX
    Explanations

    the fragment "rem" which often appears at the beginning of words

    oai_token-act-pair · gemini-2.0-flash

    rem

    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
    parsedMessage
    -0.82
     تضيفلها
    -0.76
    providedIn
    -0.73
    pile
    -0.71
    pot
    -0.71
     contextLoads
    -0.70
    p
    -0.70
    utives
    -0.70
    MigrationBuilder
    -0.70
    \{\\
    -0.69
    POSITIVE LOGITS
    და
    0.37
    HAVE
    0.37
    ToRefresh
    0.36
    وق
    0.35
    copa
    0.34
    rv
    0.34
    op
    0.34
    вто
    0.33
    draft
    0.33
    contra
    0.32
    Activations Density 0.515%

    No Known Activations