© 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. 12911
    Prev
    Next
    INDEX
    Explanations

    words ending in common suffixes

    oai_token-act-pair · gemini-2.0-flash

    Academic/formal argumentation

    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
    getMinutes
    -0.58
    WebServlet
    -0.52
     sed
    -0.50
     dead
    -0.49
    atguigu
    -0.48
    YLON
    -0.48
    /*
    -0.47
    /******/
    -0.47
    conjugated
    -0.46
    谷川
    -0.46
    POSITIVE LOGITS
    MLLoader
    0.68
     spirituality
    0.65
     toughness
    0.65
     softness
    0.65
     utafitiHapana
    0.64
     divinity
    0.64
     centralization
    0.59
     الحره
    0.59
     sufficiency
    0.59
     sobriety
    0.58
    Activations Density 1.237%

    No Known Activations