© 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. 9734
    Prev
    Next
    INDEX
    Explanations

    somewhat common English function words such as pronouns, prepositions, conjunctions, and auxillary verbs.

    oai_token-act-pair · gemini-2.0-flash

    Technical instructions

    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
     <=",
    -0.59
    Merkmale
    -0.59
    lüssel
    -0.56
     WARRANT
    -0.54
     Murch
    -0.51
    ughty
    -0.50
     Theſe
    -0.50
    poran
    -0.50
     Drives
    -0.49
     gagne
    -0.49
    POSITIVE LOGITS
     force
    0.64
    VersionUID
    0.63
    force
    0.60
    DoubleQuotes
    0.59
    setupUi
    0.54
    Force
    0.52
     FORCE
    0.50
    FORCE
    0.49
    ynb
    0.47
     INTERESAR
    0.47
    Activations Density 5.778%

    No Known Activations