© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9758
    Prev
    Next
    INDEX
    Explanations

    the preposition "around" or similar directional words

    oai_token-act-pair · gemini-2.0-flash

    around, along

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    stdafx
    -0.63
    httphttps
    -0.63
    expandindo
    -0.59
     REA
    -0.55
    出版年
    -0.55
     YP
    -0.53
    NameInMap
    -0.52
     PRS
    -0.49
     Danes
    -0.49
    /**
    -0.49
    POSITIVE LOGITS
     princesse
    0.64
     CreateTagHelper
    0.60
    verifyException
    0.58
    Kesimpulan
    0.56
    rungsseite
    0.56
    fetchone
    0.55
    脚注の使い方
    0.54
    Manbalar
    0.52
     kekurangan
    0.52
    FieldBuilder
    0.52
    Activations Density 0.601%

    No Known Activations