© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13986
    Prev
    Next
    INDEX
    Explanations

    sentences with the word "never" and sometimes other negative words.

    oai_token-act-pair · gemini-2.0-flash

    never

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     never
    -0.73
    Never
    -0.64
    /*
    -0.63
    never
    -0.62
     Never
    -0.61
    //
    -0.60
     NEVER
    -0.60
    NEVER
    -0.59
     nooit
    -0.57
    Personendaten
    -0.57
    POSITIVE LOGITS
    RUnlock
    0.63
    ฒ
    0.59
    Notae
    0.59
     Wikimedijinoj
    0.57
    IsContent
    0.56
    couverte
    0.55
    iglio
    0.54
    henswürdigkeiten
    0.54
    lapsingToolbar
    0.54
    BoxLayout
    0.52
    Activations Density 3.657%

    No Known Activations