© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 222
    Prev
    Next
    INDEX
    Explanations

    the words "follow" and "followed" and words semantically related to them such as "character" or words containing the letters "sel"

    oai_token-act-pair · gemini-2.0-flash

    follow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     follow
    -2.45
    Follow
    -2.22
    follow
    -2.19
     Follow
    -2.14
     follows
    -2.06
     followed
    -2.03
     FOLLOW
    -1.98
    follows
    -1.87
    followed
    -1.79
    FOLLOW
    -1.77
    POSITIVE LOGITS
    Geplaatst
    0.91
    MigrationBuilder
    0.84
    +#+#
    0.81
    TypedDataSet
    0.80
    RectangleBorder
    0.79
    fjspx
    0.77
    expandindo
    0.75
    tvguidetime
    0.74
     propOrder
    0.73
     EconPapers
    0.72
    Activations Density 4.487%

    No Known Activations