© 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. 2544
    Prev
    Next
    INDEX
    Explanations

    uses of pronouns referring to people and their feelings

    oai_token-act-pair · gemini-2.0-flash

    HTML and coding terminology

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

    Expressing external opinions

    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
    Their
    -2.86
     their
    -2.84
     Their
    -2.69
    their
    -2.63
     themselves
    -2.34
     THEIR
    -2.13
    themselves
    -2.00
    他们的
    -1.98
     deres
    -1.88
     kanilang
    -1.88
    POSITIVE LOGITS
     उसने
    0.69
    GEBURTSDATUM
    0.66
    httphttps
    0.65
    MigrationBuilder
    0.63
    adaptiveStyles
    0.62
    +#+
    0.60
     NSCoder
    0.58
    AddHtmlAttribute
    0.58
     nakalista
    0.58
     lui
    0.56
    Activations Density 10.647%

    No Known Activations