© 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. 14157
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and words related to exam applications

    oai_token-act-pair · gemini-2.0-flash

    Code snippets and documentation

    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
     twain
    -0.64
     pinulongan
    -0.60
    ⓧ
    -0.56
     clemen
    -0.56
    DoubleQuotes
    -0.53
    Streamer
    -0.50
    wię
    -0.49
    ocratic
    -0.49
     skjø
    -0.48
    erializer
    -0.48
    POSITIVE LOGITS
    posedge
    0.58
    oneofs
    0.48
     maxn
    0.45
     symboles
    0.45
    BuildContext
    0.43
    BaseAdapter
    0.43
    boni
    0.42
     createState
    0.42
    Égypte
    0.42
    iNdEx
    0.41
    Activations Density 7.847%

    No Known Activations