© 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. 2573
    Prev
    Next
    INDEX
    Explanations

    text from academic papers, particularly titles, authors, and publication details

    oai_token-act-pair · gemini-2.0-flash

    academic papers

    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
     AssemblyCulture
    -0.90
     ProtoMessage
    -0.83
    ſelves
    -0.78
    MemoryWarning
    -0.76
    AddTagHelper
    -0.75
    DebuggerNonUser
    -0.74
    CloseOperation
    -0.74
    UserScript
    -0.74
    WebVitals
    -0.70
    tagHelperRunner
    -0.69
    POSITIVE LOGITS
    ättning
    0.41
     ég
    0.41
    adova
    0.41
     El
    0.40
     تا
    0.40
     Dot
    0.39
     Operand
    0.39
     Ord
    0.39
     Sime
    0.38
     ta
    0.37
    Activations Density 13.398%

    No Known Activations