© 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. 16334
    Prev
    Next
    INDEX
    Explanations

    number quantities

    oai_token-act-pair · gemini-2.0-flash

    Comma

    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
     egret
    -0.34
    TagMode
    -0.34
    Trie
    -0.34
     gant
    -0.32
     pect
    -0.31
     puzz
    -0.31
     gua
    -0.31
     puffer
    -0.30
     trac
    -0.29
     fays
    -0.29
    POSITIVE LOGITS
    ,
    1.63
     ModelExpression
    0.99
    QMetaType
    0.94
     Signalez
    0.80
    RTLD
    0.79
     calendriers
    0.77
    GEBURTSDATUM
    0.77
     protoimpl
    0.73
     ProtoMessage
    0.73
    MemoryWarning
    0.73
    Activations Density 4.808%

    No Known Activations