© 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. 6997
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and punctuation that often appear near numbers or quantities or are used as numerical separators.

    oai_token-act-pair · gemini-2.0-flash

    archaic words

    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
    nesty
    -0.57
     SwiftUI
    -0.56
    minecraft
    -0.55
     OPPO
    -0.55
    lujah
    -0.54
    phem
    -0.54
    Roblox
    -0.54
    garmin
    -0.52
    bukkit
    -0.52
    rosophila
    -0.52
    POSITIVE LOGITS
     Monfieur
    1.32
     Efq
    1.31
     themſelves
    1.18
     myſelf
    1.18
     Theſe
    1.12
     Jefus
    1.07
     purpoſe
    1.07
     himſelf
    1.07
     becauſe
    1.02
     Majefty
    1.00
    Activations Density 15.482%

    No Known Activations