© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14738
    Prev
    Next
    INDEX
    Explanations

    this neuron seems to activate on question-like constructs and things that involve debate or logic.

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with "m"

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Efq
    -1.10
     purpoſe
    -1.01
     Monfieur
    -1.00
     Theſe
    -0.98
     Diſ
    -0.96
     themſelves
    -0.96
     pleaſure
    -0.95
     ſeveral
    -0.95
     reaſon
    -0.93
     quæ
    -0.90
    POSITIVE LOGITS
     N
    0.46
     m
    0.45
     ti
    0.44
     Ho
    0.44
     prom
    0.44
     ni
    0.42
     Chi
    0.41
     gez
    0.41
     Mu
    0.41
     O
    0.40
    Activations Density 1.724%

    No Known Activations