© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9095
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and political entities or organizations, frequently in the context of statements or opinions.

    oai_token-act-pair · gemini-2.0-flash

    Russia-Ukraine conflict

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     <=",
    -0.82
     Efq
    -0.81
     ſhall
    -0.71
    ſelves
    -0.71
     Monfieur
    -0.71
     Theſe
    -0.70
     ainfi
    -0.69
     becauſe
    -0.69
    principalColumn
    -0.68
     >=",
    -0.68
    POSITIVE LOGITS
    hes
    0.43
    userdetails
    0.42
    ioutil
    0.42
    地
    0.41
     Hesse
    0.41
    DialogTitle
    0.40
     dim
    0.40
    LAV
    0.39
    PARE
    0.39
    interp
    0.39
    Activations Density 7.166%

    No Known Activations