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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10567
    Prev
    Next
    INDEX
    Explanations

    descriptions of weapons or violence

    oai_token-act-pair · gemini-2.0-flash

    reflective surfaces and textures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     fieldNum
    -0.73
    uxxxx
    -0.71
     Himo
    -0.68
    تقاوى
    -0.68
     ujednoznacz
    -0.68
    ValueStyle
    -0.66
     deſt
    -0.65
     $_"
    -0.64
     becauſe
    -0.62
     ſmall
    -0.62
    POSITIVE LOGITS
     g
    0.77
     Shi
    0.75
     sh
    0.70
     mirror
    0.66
     shi
    0.65
     Mirror
    0.64
    shi
    0.63
     MIRROR
    0.60
    Shi
    0.60
     Bri
    0.58
    Activations Density 1.016%

    No Known Activations