© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3476
    Prev
    Next
    INDEX
    Explanations

    question words and words related to planning and achieving goals

    oai_token-act-pair · gemini-2.0-flash

    Asking questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     itſelf
    -0.76
     pleaſure
    -0.75
     neceff
    -0.73
     Diſ
    -0.70
     perfons
    -0.65
     Reſ
    -0.65
     himſelf
    -0.63
     nakalista
    -0.63
     fubject
    -0.62
    Does
    -0.62
    POSITIVE LOGITS
     do
    1.62
     Do
    1.13
    do
    1.09
     DO
    1.08
    Do
    1.05
     don
    0.74
     am
    0.74
    DO
    0.73
    _
    0.57
     до
    0.56
    Activations Density 1.792%

    No Known Activations