© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 3531
    Prev
    Next
    INDEX
    Explanations

    text referring to difficulties, finding something difficult, or having trouble

    oai_token-act-pair · gemini-2.0-flash

    describes difficulties and problems

    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
     difficult
    -2.58
    difficult
    -2.48
     Difficult
    -2.47
    Difficult
    -2.34
     difficulty
    -2.20
    difficulty
    -1.99
     Difficulty
    -1.96
     diffic
    -1.93
     difficulties
    -1.88
    diffic
    -1.88
    POSITIVE LOGITS
    sizeCache
    0.54
     utafitiHapana
    0.53
    phemy
    0.52
    neros
    0.52
    biskan
    0.51
    principalColumn
    0.50
    mités
    0.49
    setViewName
    0.48
    InputModule
    0.48
    chery
    0.48
    Activations Density 1.460%

    No Known Activations