© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12428
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions involving symbols like +, -, =, and characters y,x,z,B,A

    oai_token-act-pair · gemini-2.0-flash

    Code/Math/Weird Text

    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
     CCM
    -1.49
     CCA
    -1.41
     BCC
    -1.38
     NCC
    -1.34
     CCC
    -1.33
     CC
    -1.32
     PPA
    -1.32
     RCC
    -1.30
     SCC
    -1.30
     MCC
    -1.30
    POSITIVE LOGITS
     forfait
    0.45
    protoimpl
    0.44
    EndGlobalSection
    0.43
     σή
    0.42
    UnknownFieldSet
    0.40
     Tasche
    0.40
     HasFactory
    0.38
    ValueStyle
    0.38
    nonatomic
    0.38
    AttributeSet
    0.38
    Activations Density 16.832%

    No Known Activations