© 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. 14370
    Prev
    Next
    INDEX
    Explanations

    chunks of source code

    oai_token-act-pair · gemini-2.0-flash

    API requests

    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
     étoient
    -0.85
     avoient
    -0.79
     enfans
    -0.75
     skydd
    -0.74
     stället
    -0.74
     aikaa
    -0.72
     bakgrund
    -0.71
     étoit
    -0.70
     väli
    -0.69
     vandens
    -0.68
    POSITIVE LOGITS
     a
    0.52
     It
    0.52
     Don
    0.49
     In
    0.49
     He
    0.48
     Die
    0.48
     Is
    0.47
     Guys
    0.47
     Ra
    0.47
     Be
    0.47
    Activations Density 6.265%

    No Known Activations