© 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. 14749
    Prev
    Next
    INDEX
    Explanations

    uses of the word "for".

    oai_token-act-pair · gemini-2.0-flash

    prefix variations of 'for'

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

    for

    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
    rrggbb
    -0.75
    ScopeManager
    -0.71
    Personendaten
    -0.66
    usermodel
    -0.65
    Datuak
    -0.65
    complexContent
    -0.64
    CppCodeGen
    -0.63
    ImageContext
    -0.63
     AttributeSet
    -0.62
    abestanden
    -0.61
    POSITIVE LOGITS
     self
    0.52
     no
    0.52
    åd
    0.49
     free
    0.47
    elang
    0.44
     five
    0.43
     đẳng
    0.43
     Kay
    0.43
     lots
    0.41
     its
    0.41
    Activations Density 2.124%

    No Known Activations