© 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. 8864
    Prev
    Next
    INDEX
    Explanations

    the word "social"

    oai_token-act-pair · gemini-2.0-flash

    social

    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
    ſelf
    -0.91
     myſelf
    -0.88
     تانيه
    -0.87
     Jefus
    -0.85
     Monfieur
    -0.83
     houſe
    -0.82
     Houſe
    -0.81
     Eſ
    -0.80
     ſeveral
    -0.79
     faſt
    -0.79
    POSITIVE LOGITS
    ografija
    0.42
     brain
    0.42
    BagConstraints
    0.42
    ódź
    0.41
     onPostExecute
    0.40
    зумі
    0.40
    =['
    0.40
     {
    0.40
    =["
    0.39
    seck
    0.39
    Activations Density 1.629%

    No Known Activations