© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7251
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and question words

    oai_token-act-pair · gemini-2.0-flash

    Questions and answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Réponses
    -0.63
    XmlAccessType
    -0.61
    tvguidetime
    -0.61
     CWE
    -0.60
    ſelf
    -0.60
     تضيفلها
    -0.58
     surla
    -0.58
     дописавши
    -0.57
    ConverterFactory
    -0.56
     calendriers
    -0.56
    POSITIVE LOGITS
    Any
    0.67
     Any
    0.65
     any
    0.65
    any
    0.58
     moindre
    0.51
     Normdatei
    0.47
     what
    0.46
     Stoll
    0.46
    fälle
    0.46
     anybody
    0.45
    Activations Density 1.432%

    No Known Activations