© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6636
    Prev
    Next
    INDEX
    Explanations

    code snippets related to URL rewriting, specifically htaccess

    oai_token-act-pair · gemini-2.0-flash

    Greek suffixes

    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
    RenderAtEndOf
    -0.93
     سكانية
    -0.84
     '\\;'
    -0.81
    ValueStyle
    -0.79
     Normdatei
    -0.78
    UnsafeEnabled
    -0.78
     uſed
    -0.74
     Wikimedijinoj
    -0.72
     propOrder
    -0.72
    CloseOperation
    -0.71
    POSITIVE LOGITS
    σουμε
    0.73
    νονται
    0.61
    σουν
    0.59
    θηκαν
    0.59
    йся
    0.59
    йтесь
    0.57
    щены
    0.56
    етесь
    0.55
    θούν
    0.55
    шайте
    0.53
    Activations Density 4.154%

    No Known Activations