© 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. 8274
    Prev
    Next
    INDEX
    Explanations

    the word "flat" and related words in a technical-medical or business context.

    oai_token-act-pair · gemini-2.0-flash

    flat

    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
     flat
    -2.61
     Flat
    -2.58
    Flat
    -2.52
     FLAT
    -2.44
    flat
    -2.39
     Linear
    -2.17
     linear
    -2.13
    FLAT
    -2.08
    Linear
    -2.02
    linear
    -1.91
    POSITIVE LOGITS
     فريبيس
    0.60
     AssemblyVersion
    0.55
    burton
    0.50
    ByExample
    0.49
     Leck
    0.48
    DebuggerNonUser
    0.48
    olutamente
    0.48
    SharedDtor
    0.47
     dispensation
    0.47
    unately
    0.47
    Activations Density 4.454%

    No Known Activations