© 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. 6230
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are related to something being difficult

    oai_token-act-pair · gemini-2.0-flash

    difficult, hard

    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
    -0.99
     difficult
    -0.98
    difficult
    -0.95
    Difficult
    -0.93
     vanske
    -0.83
     difficulty
    -0.80
     difficiles
    -0.79
     svå
    -0.76
     vanskelig
    -0.75
     schwierig
    -0.74
    POSITIVE LOGITS
     for
    0.75
    ⓧ
    0.74
    gridx
    0.56
     الدولى
    0.53
    kuuta
    0.50
    DebuggerNonUser
    0.49
    olism
    0.49
     ExecuteAsync
    0.49
    UnknownFieldSet
    0.48
    TagHelper
    0.48
    Activations Density 5.867%

    No Known Activations