© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2227
    Prev
    Next
    INDEX
    Explanations

    words related to personal opinions about events, activities, and health

    oai_token-act-pair · gemini-2.0-flash

    about

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     صوتيه
    -0.79
     Efq
    -0.79
     becauſe
    -0.76
     Chriftian
    -0.71
     Majefty
    -0.70
     pleaſure
    -0.70
     RSSSF
    -0.69
     ostavi
    -0.69
     ſeveral
    -0.69
     juſt
    -0.68
    POSITIVE LOGITS
     the
    0.69
     this
    0.67
    antu
    0.65
     an
    0.62
     what
    0.60
     taking
    0.60
     M
    0.58
     whether
    0.58
     Sto
    0.58
     him
    0.56
    Activations Density 8.936%

    No Known Activations