© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12417
    Prev
    Next
    INDEX
    Explanations

    the possessive pronoun "my" or the capitalized word "My"

    oai_token-act-pair · gemini-2.0-flash

    My

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    KommentareTeilen
    -0.89
    findpost
    -0.82
     invokingState
    -0.81
     насељу
    -0.80
    httphttps
    -0.77
     betweenstory
    -0.76
    脚注の使い方
    -0.74
     AssemblyCompany
    -0.71
    TintMode
    -0.71
    myself
    -0.70
    POSITIVE LOGITS
     Houſe
    0.61
    ſelf
    0.61
     Majefty
    0.55
     Eſ
    0.52
     houſe
    0.51
     Resumen
    0.51
     ſer
    0.50
     greateſt
    0.49
     ſame
    0.49
     pegat
    0.48
    Activations Density 1.448%

    No Known Activations