© 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. 9003
    Prev
    Next
    INDEX
    Explanations

    instances of possessive pronouns and related words like "who"

    oai_token-act-pair · gemini-2.0-flash

    phrases related to aristocracy or nobility

    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
    GraphicsUnit
    -0.69
    Personensuche
    -0.68
     betweenstory
    -0.67
     Generales
    -0.52
    MemoryWarning
    -0.52
     الحره
    -0.51
    yntaxException
    -0.50
    bootstrapcdn
    -0.49
     tessuto
    -0.49
    Enllaces
    -0.48
    POSITIVE LOGITS
    Hauptartikel
    0.68
     ſy
    0.54
     pii
    0.52
     minnie
    0.52
     correspondent
    0.52
    ſelf
    0.52
     chamber
    0.52
    backers
    0.51
    izontal
    0.51
     companion
    0.51
    Activations Density 1.369%

    No Known Activations