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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14418
    Prev
    Next
    INDEX
    Explanations

    instances of the word "I" and "you", particularly in the context of personal experiences or beliefs.

    oai_token-act-pair · gemini-2.0-flash

    atypical word forms or spellings

    np_token-act-pair-logits · gpt-4o-mini

    which

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Ver
    -0.69
     Qu
    -0.65
     
    -0.63
     ویکی‌پدی
    -0.63
     Co
    -0.63
     Mar
    -0.62
     Par
    -0.60
     Lo
    -0.60
     Bu
    -0.60
     Mo
    -0.60
    POSITIVE LOGITS
     doubtnut
    0.86
     Theſe
    0.85
     auffi
    0.81
     Efq
    0.77
     Monfieur
    0.77
     faſt
    0.73
     ſind
    0.72
     itſelf
    0.70
     Shakspeare
    0.70
     ་་
    0.69
    Activations Density 13.821%

    No Known Activations