© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3401
    Prev
    Next
    INDEX
    Explanations

    different usages of the word "you" within text, or words related to suggestion or effort

    oai_token-act-pair · gemini-2.0-flash

    should

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     GONNA
    -0.59
    )}{(
    -0.54
    曖昧さ回避
    -0.52
    gonna
    -0.52
     Wouldn
    -0.51
     мәкалә
    -0.51
     podido
    -0.48
    րջ
    -0.47
    ebilir
    -0.46
     fuit
    -0.46
    POSITIVE LOGITS
     should
    1.37
     sh
    1.16
     Should
    0.89
     Sh
    0.86
    should
    0.84
    Sh
    0.84
    Should
    0.82
     shu
    0.82
     shou
    0.81
     sho
    0.76
    Activations Density 0.796%

    No Known Activations