© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2670
    Prev
    Next
    INDEX
    Explanations

    the word "take" or the phrase "to that"

    oai_token-act-pair · gemini-2.0-flash

    taking effect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     effects
    -2.02
     Effects
    -1.98
    Effects
    -1.84
    effects
    -1.83
     EFFECTS
    -1.72
     effets
    -1.40
    EFFECT
    -1.33
     efectos
    -1.27
     efeitos
    -1.20
    Effect
    -1.20
    POSITIVE LOGITS
    rungsseite
    0.78
    WriteBarrier
    0.68
     pinulongan
    0.67
    BeginContext
    0.63
    
    0.62
    jsxFileName
    0.58
     OMIT
    0.56
    PerformLayout
    0.55
    脚注の使い方
    0.54
     doGet
    0.54
    Activations Density 4.273%

    No Known Activations