© 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. 9860
    Prev
    Next
    INDEX
    Explanations

    instances of the number "two" appearing with related nouns and verbs.

    oai_token-act-pair · gemini-2.0-flash

    Procedures/Steps

    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
    Autoritní
    -0.71
     Roskov
    -0.69
    })$}
    -0.65
    Demografía
    -0.64
     autorytatywna
    -0.63
    BeginContext
    -0.61
     оригіналу
    -0.61
     мәкалә
    -0.60
    "):
    -0.59
     EClass
    -0.59
    POSITIVE LOGITS
     JpaRepository
    0.54
    LLocation
    0.50
    Two
    0.49
     two
    0.47
    sprechend
    0.47
    EndInit
    0.46
     Two
    0.46
    AutoresizingMask
    0.44
    DrawerToggle
    0.44
    ForResult
    0.43
    Activations Density 2.121%

    No Known Activations