© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12256
    Prev
    Next
    INDEX
    Explanations

    words related to action, function, committees and agencies

    oai_token-act-pair · gemini-2.0-flash

    activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     activities
    -1.16
     activity
    -1.15
     Activity
    -1.11
     Activities
    -1.11
    Activity
    -1.11
    activities
    -1.06
    Activities
    -1.05
    activity
    -1.02
     ACTIVITY
    -0.93
     ACTIVITIES
    -0.92
    POSITIVE LOGITS
    AccessorTable
    0.54
    醐
    0.54
    IDTH
    0.51
     thể
    0.48
    BASEPATH
    0.45
    ственность
    0.45
    Ծանոթ
    0.44
     altura
    0.44
     souffrance
    0.44
    alibaba
    0.44
    Activations Density 19.422%

    No Known Activations