© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7134
    Prev
    Next
    INDEX
    Explanations

    the word "may" and negative ability ("could not", "won't be able")

    oai_token-act-pair · gemini-2.0-flash

    technical/formal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     can
    -1.41
    can
    -1.13
     could
    -1.05
     bisa
    -0.98
     können
    -0.96
     dapat
    -0.96
    Can
    -0.96
    could
    -0.96
     Can
    -0.95
     kunnen
    -0.94
    POSITIVE LOGITS
    AccessFile
    0.49
    TagHelpers
    0.49
     ब्रेकडाउन
    0.48
     مرئيه
    0.47
    rrh
    0.47
    jsonwebtoken
    0.46
    Архівовано
    0.46
     الرياضيه
    0.45
     pinulongan
    0.44
    fetchone
    0.43
    Activations Density 1.007%

    No Known Activations