© 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. 13200
    Prev
    Next
    INDEX
    Explanations

    the presence of dates and numbers, often with high activation when slashes are involved

    oai_token-act-pair · gemini-2.0-flash

    Numbers and code

    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
     s
    -0.65
     w
    -0.65
     con
    -0.63
     fin
    -0.62
     v
    -0.61
     von
    -0.59
     pro
    -0.59
     field
    -0.59
     po
    -0.58
     sub
    -0.58
    POSITIVE LOGITS
     xenia
    0.61
     îna
    0.58
     Nip
    0.56
     MediatR
    0.55
    LLocation
    0.54
     imprimée
    0.54
     bezeichneter
    0.54
     titolata
    0.53
     Matériau
    0.52
     AttributeSet
    0.52
    Activations Density 1.649%

    No Known Activations