© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5281
    Prev
    Next
    INDEX
    Explanations

    the word "somehow".

    oai_token-act-pair · gemini-2.0-flash

    somehow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Extinguishing
    -0.91
     disambiguazione
    -0.84
    Personensuche
    -0.84
    })]
    -0.82
    RenderAtEndOf
    -0.81
    fjspx
    -0.81
     BorderRadius
    -0.78
    +#+#
    -0.78
    GeoNames
    -0.77
    ItemBackground
    -0.75
    POSITIVE LOGITS
    s
    0.57
     costuma
    0.52
     Tatsache
    0.49
    tualmente
    0.48
     بشه
    0.48
    ยว
    0.47
     minor
    0.47
     zeggen
    0.45
    情形
    0.45
     program
    0.45
    Activations Density 0.357%

    No Known Activations