© 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. 1972
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to progress

    oai_token-act-pair · gemini-2.0-flash

    words indicating proximity or progression

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

    nearness

    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
     ویکی‌پدیا
    -0.64
    tonsoft
    -0.64
     courants
    -0.63
    sizeCache
    -0.63
     Normdatei
    -0.61
    følgelig
    -0.60
    MessageOf
    -0.59
    Autoritní
    -0.59
     quæ
    -0.58
     Jefus
    -0.56
    POSITIVE LOGITS
     closer
    1.80
    closer
    1.35
     nearer
    1.32
     Closer
    1.31
     close
    1.15
    Closer
    1.07
     step
    1.02
     CLOS
    0.99
     closest
    0.90
     Close
    0.90
    Activations Density 1.197%

    No Known Activations