© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14699
    Prev
    Next
    INDEX
    Explanations

    words related to governmental dealings and political entities associated with Russia.

    oai_token-act-pair · gemini-2.0-flash

    Russia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    CppMethod
    -0.70
    GEBURTSDATUM
    -0.60
    nativeElement
    -0.59
    expandindo
    -0.56
    ItemBackground
    -0.53
    ernalia
    -0.52
    SharedCtor
    -0.52
     electrostatic
    -0.51
    UserScript
    -0.51
    مصادر
    -0.49
    POSITIVE LOGITS
     defaultstate
    0.60
    }}}}
    0.56
    ículo
    0.54
    ngrx
    0.52
    }}}{\
    0.52
    }}}\
    0.52
    AndEndTag
    0.51
     незавершена
    0.48
     äm
    0.48
     moldura
    0.47
    Activations Density 0.717%

    No Known Activations