© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 208
    Prev
    Next
    INDEX
    Explanations

    words that suggest a conditional relationship between two elements or events

    oai_token-act-pair · gemini-2.0-flash

    lack of ability/denial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    TestingModule
    -0.60
    Искәрмәләр
    -0.59
     autorytatywna
    -0.55
    டுத்த
    -0.54
    cepcion
    -0.54
    onActivityResult
    -0.54
     '/':
    -0.54
     Gill
    -0.53
    istert
    -0.51
    mband
    -0.51
    POSITIVE LOGITS
    OGND
    0.57
     perdana
    0.52
     mulighed
    0.52
     käyttää
    0.51
    djangoproject
    0.50
    rungsseite
    0.48
    __(/*!
    0.48
     namun
    0.47
    but
    0.47
    #+#
    0.47
    Activations Density 1.815%

    No Known Activations