© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3745
    Prev
    Next
    INDEX
    Explanations

    terms related to fantasy battles, worlds and deities

    oai_token-act-pair · gemini-2.0-flash

    fantastical/violent stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tvguidetime
    -1.12
     GenerationType
    -1.08
    #+#
    -1.00
    IntoConstraints
    -0.95
     Efq
    -0.94
    IUrlHelper
    -0.92
     EconPapers
    -0.88
    neſs
    -0.86
     houſe
    -0.85
    UnusedPrivate
    -0.85
    POSITIVE LOGITS
    .
    0.43
    ,
    0.40
     Fall
    0.40
     Gu
    0.40
     Yang
    0.38
     awakeFromNib
    0.38
    Fall
    0.37
     yang
    0.37
    Yang
    0.37
     bah
    0.36
    Activations Density 3.052%

    No Known Activations