© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12376
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that include dollar signs and percentages

    oai_token-act-pair · gemini-2.0-flash

    say "$"

    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
     $
    -2.70
     $\
    -1.39
     ($
    -1.36
     $(
    -1.32
     $.
    -1.30
     $-
    -1.26
     $,
    -1.23
    -$
    -1.22
    ($
    -1.21
     ${\
    -1.19
    POSITIVE LOGITS
     يتيمه
    0.76
    DockStyle
    0.65
    tagHelperRunner
    0.65
    WritableDatabase
    0.65
    RectangleBorder
    0.63
    LEncoder
    0.60
    存于互联网档案馆
    0.59
    ыгана
    0.59
     المعيارى
    0.57
    IndentedString
    0.57
    Activations Density 7.958%

    No Known Activations