© 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. 14224
    Prev
    Next
    INDEX
    Explanations

    a mix of things, specifically the string "Cs" (likely as part of a longer code), names ending in "bben", and information about the athlete Flóra Gondos including the words around it

    oai_token-act-pair · 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
     Roskov
    -0.58
    Kilder
    -0.56
    ScopeManager
    -0.54
    ichier
    -0.54
    tagHelperRunner
    -0.52
    cognised
    -0.52
    OGND
    -0.52
    twimg
    -0.52
    GIVEREF
    -0.51
     monkey
    -0.49
    POSITIVE LOGITS
     arşivlendi
    0.68
    неопр
    0.59
    SuppressLint
    0.57
     AssemblyProduct
    0.52
    NewReader
    0.52
     volna
    0.51
    IsContent
    0.50
     kellett
    0.50
    LikeLike
    0.47
    getMinutes
    0.47
    Activations Density 0.550%

    No Known Activations