© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13604
    Prev
    Next
    INDEX
    Explanations

    negative political opinions and stances

    oai_token-act-pair · gemini-2.0-flash

    Political issues

    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
    EDEFAULT
    -0.92
    principalTable
    -0.72
     continúas
    -0.63
     unknownFields
    -0.61
     виправивши
    -0.60
     Roskov
    -0.59
    featureID
    -0.57
    ">//
    -0.51
    expandindo
    -0.51
    ReusableCell
    -0.49
    POSITIVE LOGITS
     issue
    0.68
    Issue
    0.65
     Issue
    0.64
     issues
    0.63
     plank
    0.60
     platform
    0.60
    ISSUE
    0.60
     ISSUE
    0.59
    φάλ
    0.57
    issue
    0.56
    Activations Density 3.220%

    No Known Activations