© 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. 9351
    Prev
    Next
    INDEX
    Explanations

    a variety of mostly common words in the context of conversational language, without a clear theme

    oai_token-act-pair · gemini-2.0-flash

    established or older

    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
    SequentialGroup
    -0.57
     beginnetje
    -0.54
     Paglinawan
    -0.51
    الحياه
    -0.50
     Wikimedijinoj
    -0.48
    Népesség
    -0.47
    randrange
    -0.46
    LookAnd
    -0.44
    bewah
    -0.44
     <",
    -0.44
    POSITIVE LOGITS
     established
    1.70
     existing
    1.55
    established
    1.52
     veteran
    1.52
     seasoned
    1.51
     older
    1.50
     Established
    1.48
     experienced
    1.43
    existing
    1.43
     Existing
    1.41
    Activations Density 3.401%

    No Known Activations