© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 976
    Prev
    Next
    INDEX
    Explanations

    academic papers and related terms

    oai_token-act-pair · gemini-2.0-flash

    academic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    CppMethod
    -0.39
    Emit
    -0.36
    announce
    -0.35
    迦
    -0.35
    intellij
    -0.35
     übers
    -0.34
    ']):
    -0.34
     itertools
    -0.33
     par
    -0.33
     haul
    -0.33
    POSITIVE LOGITS
     Monfieur
    0.81
    VersionUID
    0.75
     Audiodateien
    0.72
     abstrait
    0.71
     purpoſe
    0.69
     Efq
    0.69
     NSCoder
    0.68
     leaſt
    0.68
     myſelf
    0.68
    DeleteBehavior
    0.67
    Activations Density 5.259%

    No Known Activations