© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1653
    Prev
    Next
    INDEX
    Explanations

    the word "begin" and close variations but not necessarily the end of the word.

    oai_token-act-pair · gemini-2.0-flash

    words related to beginnings and renewal

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

    begin

    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
    Negative Logits
    featureID
    -0.58
     SEDS
    -0.58
    boutin
    -0.58
     linkovi
    -0.54
    estar
    -0.54
     up
    -0.52
     SwitchCompat
    -0.52
     tartalomajánló
    -0.50
    )_/¯
    -0.48
     joaat
    -0.47
    POSITIVE LOGITS
     purpoſe
    0.77
     houſe
    0.69
     RIPRODUZIONE
    0.69
     pleaſure
    0.67
    ⓧ
    0.67
     Efq
    0.66
    ImageContext
    0.66
    ſelf
    0.66
     reaſon
    0.65
     CreateTagHelper
    0.65
    Activations Density 3.622%

    No Known Activations