© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3441
    Prev
    Next
    INDEX
    Explanations

    references to diversity and community, especially as it relates to student bodies

    oai_token-act-pair · gemini-2.0-flash

    improving society

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Emin
    -0.49
     оригіналу
    -0.49
    {#
    -0.48
    ophosphate
    -0.47
    enumii
    -0.47
     jeunesse
    -0.47
     ["",
    -0.46
    tamen
    -0.46
     cocks
    -0.46
     Allo
    -0.46
    POSITIVE LOGITS
    ThroughAttribute
    0.59
     propOrder
    0.53
    MigrationBuilder
    0.53
    AsUp
    0.52
     acrylique
    0.52
     pungkasnya
    0.48
     Houſe
    0.48
     righteousness
    0.47
    jooq
    0.47
     ddelweddau
    0.47
    Activations Density 8.446%

    No Known Activations