© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10672
    Prev
    Next
    INDEX
    Explanations

    references to user interfaces and program code

    oai_token-act-pair · gemini-2.0-flash

    Code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    endpush
    -0.40
    водитель
    -0.39
     ska
    -0.37
    ATR
    -0.36
    fony
    -0.36
    ("")]
    -0.35
    phine
    -0.35
    hamshire
    -0.35
     Franklin
    -0.35
    CLAIMER
    -0.34
    POSITIVE LOGITS
     EconPapers
    0.76
    ReusableCell
    0.69
    afficheront
    0.69
    Personensuche
    0.68
    Демографія
    0.68
     alphabetically
    0.66
    WriteTagHelper
    0.65
     PriorityQueue
    0.64
     stretch
    0.64
     Exactos
    0.63
    Activations Density 7.320%

    No Known Activations