© 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. 7405
    Prev
    Next
    INDEX
    Explanations

    first person possessive pronouns followed by words indicating feelings or opinion

    oai_token-act-pair · gemini-2.0-flash

    data descriptors or database terms

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

    possessive pronouns

    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
     виправивши
    -0.80
    annica
    -0.64
    aderie
    -0.56
    antMatchers
    -0.56
    PMailer
    -0.55
     turnover
    -0.54
    存于互联网档案馆
    -0.53
    illin
    -0.53
    virons
    -0.52
    σιμοποι
    -0.52
    POSITIVE LOGITS
    colgroup
    0.55
    RegressionTest
    0.52
     catto
    0.51
     ivelany
    0.50
     eyes
    0.47
     geslacht
    0.47
     kaarangay
    0.47
    DBNull
    0.46
     Roskov
    0.45
     bladder
    0.41
    Activations Density 1.428%

    No Known Activations