© 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. 5588
    Prev
    Next
    INDEX
    Explanations

    commas with words that express uncertainty or concession

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · 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
    Personensuche
    -0.90
    #+#
    -0.59
     peak
    -0.53
    ThemeOverlay
    -0.50
    usec
    -0.49
     Pha
    -0.48
    PropertyChanging
    -0.48
     pur
    -0.48
     drop
    -0.48
     Ple
    -0.47
    POSITIVE LOGITS
     suivants
    0.63
     hacerte
    0.57
    esModule
    0.56
     souten
    0.56
     متعلقه
    0.54
     gyhoeddwyd
    0.53
     nourrir
    0.52
    valently
    0.51
     suivantes
    0.51
     sachant
    0.51
    Activations Density 2.386%

    No Known Activations