© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12524
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating a negative condition or state

    oai_token-act-pair · gemini-2.0-flash

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    exitRule
    -0.66
     Efq
    -0.60
    intios
    -0.59
     المعيارى
    -0.59
     Abstr
    -0.59
    UnusedPrivate
    -0.57
    __(/*!
    -0.57
    ^(@)
    -0.56
     LoginComponent
    -0.56
     NSCoder
    -0.54
    POSITIVE LOGITS
     autorytatywna
    0.56
     ex
    0.53
    Pautan
    0.46
    uride
    0.44
     Ex
    0.44
    ńcu
    0.44
     Loomis
    0.42
    thien
    0.42
     amp
    0.42
    Ex
    0.42
    Activations Density 1.707%

    No Known Activations