© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14197
    Prev
    Next
    INDEX
    Explanations

    a mix of common words like prepositions, articles, some verbs, and some words that indicate abstract concepts like important and personal.

    oai_token-act-pair · gemini-2.0-flash

    difficult

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DebuggerNonUser
    -0.47
    셔
    -0.45
     ta
    -0.45
    ="@+
    -0.42
     lalu
    -0.41
    ksis
    -0.40
    ($(
    -0.39
     فريبيس
    -0.39
    TagHelper
    -0.39
    田
    -0.39
    POSITIVE LOGITS
     hard
    1.61
     tough
    1.59
     difficult
    1.51
     Tough
    1.34
    Tough
    1.33
    difficult
    1.33
     Hard
    1.31
    hard
    1.31
    Hard
    1.31
     Difficult
    1.29
    Activations Density 2.515%

    No Known Activations