© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6120
    Prev
    Next
    INDEX
    Explanations

    text containing the words "I", "is", and personal judgements like "better", "hard".

    oai_token-act-pair · gemini-2.0-flash

    subjectivity

    np_max-act-logits · 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
     picioare
    -1.07
     maș
    -0.93
     înal
    -0.91
     viață
    -0.86
     căr
    -0.86
     culoare
    -0.85
     Dumnezeu
    -0.85
     băr
    -0.84
     gând
    -0.84
     îna
    -0.83
    POSITIVE LOGITS
     su
    0.93
     com
    0.86
     des
    0.83
     compiti
    0.79
     sus
    0.78
     reci
    0.78
     inte
    0.77
     espec
    0.77
     rec
    0.77
     appro
    0.77
    Activations Density 7.802%

    No Known Activations