© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6781
    Prev
    Next
    INDEX
    Explanations

    the word bit often followed by an adjective

    oai_token-act-pair · gemini-2.0-flash

    adjectives describing things negatively

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

    Negative adjectives

    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
     فريبيس
    -0.75
    muito
    -0.72
     Очень
    -0.71
    очень
    -0.71
     sangat
    -0.71
    quite
    -0.70
     Quite
    -0.70
    Extremely
    -0.69
     quite
    -0.69
    Very
    -0.69
    POSITIVE LOGITS
     strange
    0.61
     weird
    0.59
     sad
    0.58
     odd
    0.57
    protoimpl
    0.53
    Linq
    0.51
     silly
    0.51
     creepy
    0.50
    strange
    0.50
    }{*}{
    0.46
    Activations Density 0.842%

    No Known Activations