© 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. 16058
    Prev
    Next
    INDEX
    Explanations

    uses of the word "I", "no", "that", "it", or "someone"

    oai_token-act-pair · gemini-2.0-flash

    Explanations and definitions

    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
     mean
    -2.98
     Mean
    -2.70
    mean
    -2.64
    Mean
    -2.52
     MEAN
    -2.45
    means
    -2.44
     means
    -2.38
     Means
    -2.36
    Means
    -2.30
     MEANS
    -2.23
    POSITIVE LOGITS
    Autoritní
    0.69
     iNdEx
    0.63
    PerformLayout
    0.62
    yntaxException
    0.60
     royaume
    0.59
    دانشنامهٔ
    0.58
    ContentAlignment
    0.57
    Rhestr
    0.57
    SBATCH
    0.57
     oprot
    0.57
    Activations Density 9.203%

    No Known Activations