© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10673
    Prev
    Next
    INDEX
    Explanations

    the word "regional"

    oai_token-act-pair · gemini-2.0-flash

    regional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    \{\\
    -0.96
    تقاوى
    -0.93
     "..\..\..\
    -0.90
     صوتيه
    -0.88
    BeginContext
    -0.87
    enumi
    -0.84
    OGND
    -0.81
    Portail
    -0.79
    KURZBESCHREIBUNG
    -0.77
    ollectionView
    -0.76
    POSITIVE LOGITS
     appartiennent
    0.58
     prenn
    0.57
     Ophelia
    0.56
     Espagne
    0.54
     Fø
    0.53
     哈
    0.52
     kysy
    0.52
     giudi
    0.52
     CAC
    0.52
     pfalz
    0.52
    Activations Density 0.787%

    No Known Activations