© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8625
    Prev
    Next
    INDEX
    Explanations

    what appears to be citations or references, including numbers, letters like F, E, or D, and punctuation

    oai_token-act-pair · gemini-2.0-flash

    Dates and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    2
    -2.03
    ２
    -1.15
     twenty
    -0.98
    ۲
    -0.93
     Twenty
    -0.90
    ২
    -0.89
    २
    -0.88
     two
    -0.88
     ২
    -0.80
     ۲
    -0.79
    POSITIVE LOGITS
    IVEREF
    0.60
     ProtoMessage
    0.54
     createState
    0.53
    fjspx
    0.53
    ochim
    0.52
    IntoConstraints
    0.50
    HomeAsUpEnabled
    0.50
    featureID
    0.48
    MLLoader
    0.47
    webElementXpaths
    0.47
    Activations Density 4.324%

    No Known Activations