© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9487
    Prev
    Next
    INDEX
    Explanations

    text between quotation marks and some Kannada language words

    oai_token-act-pair · gemini-2.0-flash

    Mixed languages, code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Platon
    -0.62
     Mahomet
    -0.56
     Agamemnon
    -0.56
     Talon
    -0.55
     Tiberius
    -0.55
     Deuteronomy
    -0.54
     Chaldean
    -0.53
     Ophelia
    -0.52
     TMP
    -0.52
     Pilate
    -0.52
    POSITIVE LOGITS
    حوالہ
    0.61
    rungsseite
    0.60
     resourceCulture
    0.55
    hütte
    0.54
    yelidikan
    0.54
     McQu
    0.52
     Sorensen
    0.51
    atility
    0.51
    lösen
    0.50
     McCormack
    0.50
    Activations Density 8.875%

    No Known Activations