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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4979
    Prev
    Next
    INDEX
    Explanations

    words related to the French language, mixed with URLs, numbers, and symbols

    oai_token-act-pair · gemini-2.0-flash

    Numbers and units

    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
    +#+#
    -0.48
    φάλ
    -0.46
    WebKit
    -0.43
    PullParser
    -0.43
    ServletException
    -0.42
    صبحت
    -0.39
    pinned
    -0.36
     notch
    -0.35
    روش
    -0.35
     partito
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.83
    الحياه
    0.73
    gouv
    0.68
     Romains
    0.67
    RegistryLite
    0.66
     ProtoMessage
    0.66
    DeleteBehavior
    0.64
     AttributeSet
    0.62
    sizeCache
    0.62
    erus
    0.60
    Activations Density 9.365%

    No Known Activations