© 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. 12477
    Prev
    Next
    INDEX
    Explanations

    words related to planning and construction, or numbers in the context of lists, pages, or years.

    oai_token-act-pair · gemini-2.0-flash

    legal, investigations, apartments

    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
    NUMX
    -0.69
    seamnă
    -0.57
    ÚBL
    -0.56
    çuk
    -0.54
    уза
    -0.51
     indépendant
    -0.50
     oorlog
    -0.49
     getCode
    -0.48
     MessageBoxIcon
    -0.48
     Lyft
    -0.48
    POSITIVE LOGITS
     linkovi
    0.84
    LookAnd
    0.67
    didSet
    0.66
    parsedMessage
    0.61
    #+#
    0.60
    writeFieldEnd
    0.59
    GEBURTSDATUM
    0.59
    SharedCtor
    0.59
     Walkover
    0.59
    الحياه
    0.57
    Activations Density 12.340%

    No Known Activations