© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8611
    Prev
    Next
    INDEX
    Explanations

    inconsistent text including code, names, email addresses, and other developer related words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    um
    -0.38
    us
    -0.37
    ja
    -0.35
    lu
    -0.32
    ur
    -0.32
    ly
    -0.31
    ys
    -0.31
    cal
    -0.31
    ky
    -0.30
    sok
    -0.30
    POSITIVE LOGITS
     оригіналу
    0.71
    anskje
    0.67
    :+:
    0.67
    awtextra
    0.67
     mergeFrom
    0.65
    $_['
    0.64
     numerus
    0.62
     surla
    0.61
    hastly
    0.61
    phazard
    0.60
    Activations Density 9.217%

    No Known Activations