© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7997
    Prev
    Next
    INDEX
    Explanations

    german text with grammatical structure, possibly discussing modal verbs.

    oai_token-act-pair · gemini-2.0-flash

    man

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     der
    -0.61
    يتر
    -0.59
     يتيمه
    -0.57
    Datuak
    -0.57
    Puss
    -0.54
     Estrada
    -0.54
    Hauptartikel
    -0.53
    AsStream
    -0.53
     ab
    -0.53
    enda
    -0.52
    POSITIVE LOGITS
     itſelf
    0.83
     autorytatywna
    0.79
     zelve
    0.76
     theſe
    0.76
    ñores
    0.75
     Voyez
    0.72
     héri
    0.72
     disambiguazione
    0.71
     Monfieur
    0.71
    kháu
    0.68
    Activations Density 0.133%

    No Known Activations