© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14883
    Prev
    Next
    INDEX
    Explanations

    descriptions of sexual harassment in the workplace

    oai_token-act-pair · gemini-2.0-flash

    words related to a safe workplace environment

    np_token-act-pair-logits · gpt-4o-mini

    safety and friendliness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ि
    -0.45
    валі
    -0.44
    makeConstraints
    -0.43
    onViewCreated
    -0.43
    ε
    -0.42
    Referanser
    -0.42
     zako
    -0.41
    bbler
    -0.41
    ună
    -0.40
    vann
    -0.40
    POSITIVE LOGITS
     safe
    0.92
     hospitable
    0.85
    safe
    0.85
     welcoming
    0.81
     Safe
    0.80
    Safe
    0.77
    DockStyle
    0.76
     SAFE
    0.75
     safer
    0.75
     friendly
    0.74
    Activations Density 1.804%

    No Known Activations