© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7996
    Prev
    Next
    INDEX
    Explanations

    words related to magic and mythical stories

    oai_token-act-pair · gemini-2.0-flash

    Actions and changes

    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
     EconPapers
    -1.13
     تضيفلها
    -0.95
     nahilalakip
    -0.94
     pleaſure
    -0.84
     myſelf
    -0.82
     '\\;'
    -0.79
     doInBackground
    -0.79
    IntoConstraints
    -0.79
    ^(@)
    -0.79
     raiſ
    -0.79
    POSITIVE LOGITS
    WithMany
    0.49
     ak
    0.45
     f
    0.43
     so
    0.43
     b
    0.42
     do
    0.40
     tak
    0.39
    rie
    0.39
     Bl
    0.38
    thode
    0.38
    Activations Density 0.411%

    No Known Activations