© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15660
    Prev
    Next
    INDEX
    Explanations

    words related to legal disputes and expressing opinions

    oai_token-act-pair · gemini-2.0-flash

    desires or requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     effort
    -0.63
    ♥♥
    -0.54
     *=
    -0.54
     efforts
    -0.52
     vigorously
    -0.51
     Effort
    -0.50
     vehement
    -0.50
    態
    -0.49
     strongly
    -0.49
     ho
    -0.48
    POSITIVE LOGITS
     régal
    0.66
    CppMethod
    0.65
     Monfieur
    0.65
     pleaſure
    0.65
     houſe
    0.63
     ſeveral
    0.61
     Efq
    0.61
    awtextra
    0.60
     ſtate
    0.59
     يتيمه
    0.59
    Activations Density 10.897%

    No Known Activations