© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5104
    Prev
    Next
    INDEX
    Explanations

    the letter "N" and emotionally charged, negative language.

    oai_token-act-pair · 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
    GraphicsUnit
    -0.74
    httphttps
    -0.71
    Identyfik
    -0.69
     referenties
    -0.68
     صوتيه
    -0.67
    MemoryWarning
    -0.65
     nakalista
    -0.64
     betweenstory
    -0.64
    IsContent
    -0.63
     архивлан
    -0.63
    POSITIVE LOGITS
     reporting
    0.55
    luiting
    0.50
     REPORTING
    0.44
     per
    0.43
    แจ
    0.41
    putan
    0.40
     Reporting
    0.40
    losis
    0.39
    ivasan
    0.39
    фан
    0.39
    Activations Density 5.165%

    No Known Activations