© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9706
    Prev
    Next
    INDEX
    Explanations

    negations in non-English text, possibly Croatian or a Slavic language

    oai_token-act-pair · gemini-2.0-flash

    "not"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     also
    -0.64
    (!__
    -0.59
     not
    -0.58
     non
    -0.53
     capital
    -0.52
    amination
    -0.49
    squareup
    -0.49
    liothèque
    -0.49
     -
    -0.47
    рослав
    -0.47
    POSITIVE LOGITS
     مشين
    0.70
     autorytatywna
    0.69
     nakalista
    0.63
    RegressionTest
    0.63
    UpInside
    0.59
    numerusform
    0.57
    MLLoader
    0.56
    AnchorStyles
    0.55
     Sociological
    0.53
     Diz
    0.52
    Activations Density 0.294%

    No Known Activations