© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9765
    Prev
    Next
    INDEX
    Explanations

    the word "direct"

    oai_token-act-pair · gemini-2.0-flash

    direct

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.94
     and
    -0.77
      
    -0.73
    f
    -0.73
    !
    -0.72
    .
    -0.71
     in
    -0.71
    in
    -0.71
    ;
    -0.69
    en
    -0.69
    POSITIVE LOGITS
     myſelf
    1.36
     Efq
    1.35
    ^(@)
    1.33
     Theſe
    1.29
     doubtnut
    1.28
     Monfieur
    1.27
     Jefus
    1.21
     Eſ
    1.16
     Houſe
    1.13
    IBLIO
    1.09
    Activations Density 1.698%

    No Known Activations