© 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. 12637
    Prev
    Next
    INDEX
    Explanations

    the combination of the words "in", and words related to fantasy and crafting

    oai_token-act-pair · gemini-2.0-flash

    plate

    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
     suit
    -0.56
     مشين
    -0.50
    GrantedAuthority
    -0.48
    urysty
    -0.47
    IBarButtonItem
    -0.47
    suit
    -0.46
     Suit
    -0.44
    "}")
    -0.43
    abetes
    -0.41
    Suit
    -0.41
    POSITIVE LOGITS
     plate
    0.84
     Plate
    0.78
    PLATE
    0.75
    plate
    0.75
     PLATE
    0.74
    Plate
    0.72
     Baillargeon
    0.71
     tap
    0.70
    createCanvas
    0.69
    plates
    0.62
    Activations Density 4.393%

    No Known Activations