© 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. 2797
    Prev
    Next
    INDEX
    Explanations

    Latex, code, and math notation

    oai_token-act-pair · gemini-2.0-flash

    _

    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
     MF
    -1.51
     CF
    -1.46
     AF
    -1.45
     LF
    -1.45
     PF
    -1.42
     DF
    -1.42
     WF
    -1.41
     HF
    -1.39
     NF
    -1.38
     GF
    -1.38
    POSITIVE LOGITS
    ArrowToggle
    0.52
    енча
    0.47
     Administrativna
    0.46
    Chham
    0.45
     kaynağından
    0.44
    SourceChecksum
    0.43
     Ingram
    0.43
     Knie
    0.43
     Camara
    0.43
    ⓧ
    0.42
    Activations Density 47.780%

    No Known Activations