© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12148
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns or the word "pregnant"

    oai_token-act-pair · gemini-2.0-flash

    first-person statements

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

    I am

    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
     comigo
    -0.73
     تانيه
    -0.51
     пей
    -0.50
     facie
    -0.49
     történ
    -0.48
     proprement
    -0.48
     manifestazione
    -0.48
     conmigo
    -0.47
     auft
    -0.47
     idéale
    -0.47
    POSITIVE LOGITS
    IsContent
    0.87
    migrationBuilder
    0.79
    Autoritní
    0.77
    httphttps
    0.74
    ArgsConstructor
    0.69
    ReusableCell
    0.67
    Geplaatst
    0.67
     ISNI
    0.66
    WillAppear
    0.65
    niająca
    0.65
    Activations Density 0.710%

    No Known Activations