© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6307
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to expressing an opinion or sentiment about political actions

    oai_token-act-pair · gemini-2.0-flash

    expressing opinions, feelings, support

    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
     unknownFields
    -0.82
     Theſe
    -0.82
    __':
    -0.82
     Efq
    -0.81
     myſelf
    -0.79
     Monfieur
    -0.79
     كومونز
    -0.78
    setVerticalGroup
    -0.78
    InjectAttribute
    -0.72
    MessageOf
    -0.72
    POSITIVE LOGITS
    vi
    0.47
    一分
    0.45
     reservations
    0.44
     tre
    0.43
     par
    0.43
     Hack
    0.42
     reservas
    0.41
     geste
    0.41
    sien
    0.41
     reservation
    0.41
    Activations Density 1.370%

    No Known Activations