© 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. 12435
    Prev
    Next
    INDEX
    Explanations

    the letters "th" and "sh", and sometimes "it" and "ih"

    oai_token-act-pair · gemini-2.0-flash

    words and phrases related to health and wellness

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

    th

    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
    MigrationBuilder
    -0.75
    /**
    -0.73
    WireFormatLite
    -0.69
     "..\..\
    -0.65
    SourceChecksum
    -0.65
     "..\..\..\
    -0.65
    ConstraintMaker
    -0.64
    Personendaten
    -0.61
     виправивши
    -0.60
     nahilalakip
    -0.60
    POSITIVE LOGITS
    aven
    0.54
     سكانية
    0.54
    ave
    0.53
     оригіналу
    0.51
     lot
    0.50
    hdessä
    0.50
    λης
    0.47
    sodik
    0.47
    เฉพาะ
    0.46
     douleurs
    0.46
    Activations Density 0.312%

    No Known Activations