© 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. 9849
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "clarity" or things related to "understanding".

    oai_token-act-pair · gemini-2.0-flash

    clarity

    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
     He
    -0.64
     But
    -0.63
    th
    -0.63
    cal
    -0.61
     So
    -0.59
     re
    -0.57
     The
    -0.57
     Her
    -0.57
    G
    -0.56
     H
    -0.56
    POSITIVE LOGITS
     Theſe
    1.19
     itſelf
    1.09
     myſelf
    1.06
     feroit
    1.05
     auffi
    1.04
     ainfi
    1.03
     auroit
    1.02
     étoit
    1.02
     RIPRODUZIONE
    1.02
    ſelf
    0.99
    Activations Density 4.208%

    No Known Activations