© 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. 10904
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on a wide range of seemingly unrelated words and phrases, but with a common thread of being part of logical expressions or steps in a process (mathematical, coding, reasoning, etc.)

    oai_token-act-pair · gemini-2.0-flash

    Rate calculations

    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
    hoeddwyd
    -0.66
    ContentAsync
    -0.64
    CodedInputStream
    -0.62
     demografica
    -0.62
     himo
    -0.60
     Himo
    -0.59
    IsMutable
    -0.59
    MigrationBuilder
    -0.57
    Демографія
    -0.57
    argout
    -0.57
    POSITIVE LOGITS
    weiler
    0.58
    conomie
    0.54
     N
    0.53
    *\
    0.50
    auri
    0.49
    روابط
    0.49
     {\
    0.48
    PYX
    0.48
    enburg
    0.48
    endorf
    0.48
    Activations Density 3.811%

    No Known Activations