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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14297
    Prev
    Next
    INDEX
    Explanations

    characters in fictional stories, especially aliens, their descriptions, and their relationships to other characters.

    oai_token-act-pair · gemini-2.0-flash

    character/event descriptions

    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
     esternos
    -0.82
     saites
    -0.78
    SharedDtor
    -0.71
    MigrationBuilder
    -0.70
    FunctionFlags
    -0.64
     don
    -0.63
    handles
    -0.60
    تقاوى
    -0.59
    بوابة
    -0.59
     arşivlendi
    -0.59
    POSITIVE LOGITS
     réglable
    0.48
     spatula
    0.46
    出版年
    0.45
     '@/
    0.44
     bì
    0.42
    SBATCH
    0.42
    yargs
    0.42
     fermée
    0.41
     setuptools
    0.41
     geografia
    0.40
    Activations Density 5.572%

    No Known Activations