© 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. 14179
    Prev
    Next
    INDEX
    Explanations

    C code that defines hexadecimal masks

    oai_token-act-pair · gemini-2.0-flash

    prefixes and structures in programming languages

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

    x

    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
     oprot
    -0.64
     Chwiliwch
    -0.60
     defaultstate
    -0.59
     kasarigan
    -0.56
    Autoritní
    -0.51
    httphttps
    -0.50
    TagHelper
    -0.49
     tetrachloride
    -0.49
     sqlalchemy
    -0.49
    posób
    -0.48
    POSITIVE LOGITS
    enumi
    0.85
     Conſ
    0.55
     ögon
    0.54
    oen
    0.48
    StoreMessageInfo
    0.48
    ikiki
    0.48
    onse
    0.48
    verwijspagina
    0.46
     verste
    0.45
    maz
    0.45
    Activations Density 2.470%

    No Known Activations