© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15889
    Prev
    Next
    INDEX
    Explanations

    code comments and related symbols

    oai_token-act-pair · gemini-2.0-flash

    Code comments

    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
    
    -0.67
    ScopeManager
    -0.63
     a
    -0.59
    webElementXpaths
    -0.57
    istoitu
    -0.56
     this
    -0.55
     fides
    -0.55
    Reducer
    -0.54
    AYO
    -0.54
     being
    -0.53
    POSITIVE LOGITS
     Performs
    0.72
     Adds
    0.71
     Allows
    0.71
     Prevents
    0.66
     Generates
    0.65
     Enables
    0.64
     Uses
    0.64
     avoient
    0.63
     anún
    0.63
     Sends
    0.62
    Activations Density 9.501%

    No Known Activations