© 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. 15310
    Prev
    Next
    INDEX
    Explanations

    fragments, possibly incomplete words or parts of words, often followed or preceded by other characters.

    oai_token-act-pair · gemini-2.0-flash

    words starting with "sC" where C is a consonant

    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
     doInBackground
    -0.56
     ویکی‌آمباردا
    -0.51
     SqlParameter
    -0.50
    migrationBuilder
    -0.48
     knex
    -0.48
     Lumpur
    -0.48
     MessageBoxIcon
    -0.47
    Collegamenti
    -0.47
     PB
    -0.47
     EClass
    -0.46
    POSITIVE LOGITS
    rashed
    0.56
     chré
    0.56
    ArgumentParser
    0.54
    ardom
    0.53
     étoit
    0.53
    roaches
    0.51
     neuve
    0.51
    ARKS
    0.50
    unched
    0.50
    rors
    0.50
    Activations Density 7.675%

    No Known Activations