© 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. 9171
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions such as "of", "with", or "for" or words relating to the outdoors

    oai_token-act-pair · gemini-2.0-flash

    words related to navigation and guidance

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

    guide

    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
    MessageOf
    -0.70
    setVerticalGroup
    -0.69
    contentLoaded
    -0.67
    __':
    -0.66
     defaultstate
    -0.62
    IndentedString
    -0.57
    ContentAsync
    -0.56
    __':
    -0.53
    Tikang
    -0.53
     للمعارف
    -0.53
    POSITIVE LOGITS
     guide
    1.13
     guides
    1.06
     directions
    1.02
    Guide
    0.93
    guide
    0.93
     Guide
    0.93
    directions
    0.90
     guía
    0.85
    guides
    0.84
     Directions
    0.84
    Activations Density 1.510%

    No Known Activations