© 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. 3830
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and related verbs

    oai_token-act-pair · gemini-2.0-flash

    I

    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
     @"/
    -0.63
    toso
    -0.60
     ProtoMessage
    -0.59
     ujednoznacz
    -0.59
    ParallelGroup
    -0.58
    scryfall
    -0.58
    Tikang
    -0.57
    ➟
    -0.55
     continúas
    -0.55
    writerow
    -0.54
    POSITIVE LOGITS
     exercised
    0.54
     bled
    0.50
     exercise
    0.45
    EXERC
    0.44
     Fieber
    0.44
    jdź
    0.44
    odine
    0.44
     EXERCISE
    0.43
     cried
    0.43
     exercising
    0.42
    Activations Density 1.468%

    No Known Activations