© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3316
    Prev
    Next
    INDEX
    Explanations

    a variety of common English words, with a slight preference for the word "you" and the phrase "to".

    oai_token-act-pair · gemini-2.0-flash

    code/API

    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
    󠁣
    -0.63
    칙
    -0.54
    kuuta
    -0.51
     VizieR
    -0.51
    iços
    -0.48
    ginous
    -0.47
    جی
    -0.47
     Stellen
    -0.46
    Abit
    -0.46
     runtime
    -0.46
    POSITIVE LOGITS
     للاسماء
    0.68
     ModelExpression
    0.61
    jstor
    0.59
    Autoritní
    0.56
    AttributeSet
    0.56
     Signalez
    0.56
    IonicModule
    0.56
    ]$}
    0.54
    istungen
    0.54
     lèvres
    0.52
    Activations Density 0.837%

    No Known Activations