© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6866
    Prev
    Next
    INDEX
    Explanations

    language about company liability related to employee health, safety, and community.

    oai_token-act-pair · gemini-2.0-flash

    safety

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    +:+
    -0.81
    StoryboardSegue
    -0.68
    MemoryWarning
    -0.68
    WriteBarrier
    -0.68
    XmlAccessType
    -0.63
    DrawerToggle
    -0.63
    исленность
    -0.62
     مشين
    -0.61
    ISupport
    -0.60
    AutoresizingMask
    -0.59
    POSITIVE LOGITS
     safety
    2.55
     safe
    2.25
     Safety
    2.22
    safety
    2.19
    Safety
    2.16
     safely
    2.08
     safer
    2.08
     SAFETY
    2.02
    safe
    2.00
     Safe
    2.00
    Activations Density 0.768%

    No Known Activations