© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4539
    Prev
    Next
    INDEX
    Explanations

    phrases related to life events or changes over time

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     again
    -2.83
    again
    -2.50
    Again
    -2.45
     Again
    -2.42
     AGAIN
    -2.13
     novamente
    -2.06
     nuevamente
    -1.89
     opět
    -1.79
     nuovamente
    -1.76
     опять
    -1.74
    POSITIVE LOGITS
    Datuak
    0.63
    estors
    0.60
    UrlResolution
    0.60
     Faso
    0.59
    Disliked
    0.54
    })->
    0.54
    KeySpec
    0.53
    wpi
    0.53
    utella
    0.50
    itiers
    0.49
    Activations Density 1.901%

    No Known Activations