© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16223
    Prev
    Next
    INDEX
    Explanations

    strings related to file paths, code snippets, and string manipulation

    oai_token-act-pair · gemini-2.0-flash

    say "str word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Str
    -2.08
     str
    -1.92
     STR
    -1.88
    Str
    -1.88
     Stri
    -1.73
    STR
    -1.70
    str
    -1.69
     Stre
    -1.64
    Stri
    -1.58
     Stra
    -1.54
    POSITIVE LOGITS
     Mejía
    0.58
    DockStyle
    0.51
     Elise
    0.48
     TÜV
    0.48
     CEC
    0.48
    TOY
    0.45
     kaarangay
    0.45
     Palacios
    0.44
    qtype
    0.43
     TOY
    0.43
    Activations Density 1.056%

    No Known Activations