© 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. 4332
    Prev
    Next
    INDEX
    Explanations

    fragmented non-English sentences or gibberish that sometimes contains words or partial words with accents

    oai_token-act-pair · gemini-2.0-flash

    French language

    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
     findOne
    -0.60
     surla
    -0.55
    </tr>
    -0.52
    wic
    -0.51
     Gemeinden
    -0.50
    HostException
    -0.50
    ல்
    -0.50
    توض
    -0.49
    WebControls
    -0.48
    iblichen
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.58
    SharedDtor
    0.52
    RectangleBorder
    0.50
     poitrine
    0.50
     AssemblyProduct
    0.49
     Superhost
    0.49
    adpleegd
    0.48
     Roskov
    0.47
     fourrure
    0.47
     peine
    0.46
    Activations Density 0.573%

    No Known Activations