© 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. 4625
    Prev
    Next
    INDEX
    Explanations

    words related to different skills and professions

    oai_token-act-pair · gemini-2.0-flash

    words related to skills and techniques

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

    skills

    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
    mobileqq
    -0.53
     Roskov
    -0.52
    saraba
    -0.50
    liferay
    -0.47
    mybatisplus
    -0.47
     backless
    -0.44
    uração
    -0.44
    DrawerLayout
    -0.44
     SqlParameter
    -0.44
    DrawerToggle
    -0.43
    POSITIVE LOGITS
     skills
    0.92
     Skills
    0.78
     Techniques
    0.75
     techniques
    0.74
     styles
    0.74
     style
    0.73
    skills
    0.73
     SKILLS
    0.73
     technique
    0.71
    sstil
    0.69
    Activations Density 1.350%

    No Known Activations