© 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. 4958
    Prev
    Next
    INDEX
    Explanations

    snippets of computer code and fantasy book descriptions, specifically focusing on resources, magic, fighting, and negative aspects of fantasy worlds.

    oai_token-act-pair · gemini-2.0-flash

    magic/fantasy

    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
     Magic
    -2.09
     magic
    -2.06
    Magic
    -2.02
     magical
    -1.98
     MAGIC
    -1.91
    magic
    -1.88
    MAGIC
    -1.76
     Magical
    -1.74
    magical
    -1.71
    Magical
    -1.63
    POSITIVE LOGITS
    fony
    0.59
    ushima
    0.50
    IVEREF
    0.48
     Peaches
    0.45
    enumi
    0.44
    Enclosure
    0.44
    stahl
    0.42
    PROTE
    0.41
    RAINT
    0.40
    Gemeinde
    0.40
    Activations Density 1.551%

    No Known Activations