© 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. 11607
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, numbers and other non-alphanumeric characters, many of which are followed or preceded by letters.

    oai_token-act-pair · 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
    TagMode
    -0.85
     متعلقه
    -0.71
     BorderRadius
    -0.70
    DoubleQuotes
    -0.64
    AnchorStyles
    -0.59
    Kanpo
    -0.59
     InputDecoration
    -0.56
    stdc
    -0.56
    abetes
    -0.56
     AssemblyCulture
    -0.55
    POSITIVE LOGITS
     gouttes
    0.75
     genoux
    0.71
     he
    0.69
     Romains
    0.63
     skolen
    0.63
     it
    0.63
     dalamnya
    0.62
     navires
    0.62
     that
    0.61
     peintures
    0.60
    Activations Density 18.153%

    No Known Activations