© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14829
    Prev
    Next
    INDEX
    Explanations

    mathematical and trigonometric code statements

    oai_token-act-pair · 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
     */;
    -0.91
    */;
    -0.86
    %");
    -0.79
    !")
    
    -0.79
    )»
    -0.78
    */)
    -0.77
    .",
    
    -0.74
    .},
    -0.73
    .].
    -0.73
    ";}
    -0.73
    POSITIVE LOGITS
    sizeCache
    0.78
    GEBURTSDATUM
    0.73
    StructEnd
    0.69
     piaci
    0.68
    textTheme
    0.66
     surla
    0.61
    TemporalType
    0.60
    Tazama
    0.59
    الإنجليزية
    0.58
    الحياه
    0.58
    Activations Density 7.426%

    No Known Activations