© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14430
    Prev
    Next
    INDEX
    Explanations

    excerpts of discussions about language usage and grammar

    oai_token-act-pair · gemini-2.0-flash

    definitions of words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     spot
    -0.40
     betweenstory
    -0.40
    usive
    -0.40
    ReadKey
    -0.40
     cac
    -0.39
     ex
    -0.38
     Zug
    -0.38
     plu
    -0.37
     correct
    -0.36
     Bef
    -0.36
    POSITIVE LOGITS
     AssemblyCulture
    0.86
     Савезне
    0.75
    NameInMap
    0.69
     فريبيس
    0.68
    Personendaten
    0.67
    Datuak
    0.67
    twimg
    0.66
     ModelExpression
    0.66
    httphttps
    0.65
    ⓧ
    0.65
    Activations Density 14.538%

    No Known Activations