© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10731
    Prev
    Next
    INDEX
    Explanations

    words and phrases that end in "ing", "ly", and "ander" along with some band names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     déjeuner
    -0.51
    ngan
    -0.50
    zeg
    -0.48
    Попис
    -0.48
     tenaga
    -0.46
     lại
    -0.45
     emphasis
    -0.45
     στιγ
    -0.45
     almoço
    -0.44
     Opening
    -0.44
    POSITIVE LOGITS
     wander
    0.96
     wandering
    0.82
    wander
    0.81
     stray
    0.81
     roaming
    0.78
     noma
    0.77
     Wandering
    0.77
     roam
    0.76
     nomadic
    0.73
     Wanderers
    0.73
    Activations Density 1.168%

    No Known Activations