© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2735
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns with auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    first-person pronouns

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    CrossRef
    -0.43
    int
    -0.39
    band
    -0.39
     ме
    -0.36
    ल
    -0.36
    si
    -0.35
    tie
    -0.34
    PG
    -0.34
    oria
    -0.34
     FD
    -0.33
    POSITIVE LOGITS
     intptr
    1.07
     disambiguazione
    1.02
     lenker
    0.96
     للمعارف
    0.91
     Italijanski
    0.89
     himo
    0.88
    Autoritní
    0.85
    AutoScaleMode
    0.83
    NameInMap
    0.83
    writeFieldEnd
    0.81
    Activations Density 0.584%

    No Known Activations