© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2969
    Prev
    Next
    INDEX
    Explanations

    the word "action" and sometimes finds the word "properly"

    oai_token-act-pair · gemini-2.0-flash

    legal and appropriate context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -1.58
     itſelf
    -1.53
     Shakspeare
    -1.32
     Theſe
    -1.26
     raiſ
    -1.26
     ſtate
    -1.25
     ―――――
    -1.23
     Anſ
    -1.23
     poffible
    -1.23
     pleaſure
    -1.23
    POSITIVE LOGITS
     a
    0.97
    ,
    0.90
     the
    0.86
     an
    0.79
     (
    0.77
     as
    0.69
     are
    0.68
     her
    0.68
     has
    0.68
     and
    0.67
    Activations Density 0.747%

    No Known Activations