© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10624
    Prev
    Next
    INDEX
    Explanations

    words that reflect a critical or questioning point of view in a business, legal, technical or general context.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     this
    -2.69
    this
    -2.20
     questo
    -1.57
    This
    -1.54
     acest
    -1.52
     questa
    -1.51
     This
    -1.47
     هذا
    -1.41
     THIS
    -1.41
     этого
    -1.35
    POSITIVE LOGITS
     وہ
    0.48
    imageshack
    0.47
    HERE
    0.46
     Here
    0.45
     Today
    0.44
    گانه
    0.44
    Erreferentziak
    0.44
     therein
    0.44
    ActionPerformed
    0.43
    那里
    0.43
    Activations Density 11.101%

    No Known Activations