© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3733
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to a group of people acting, often violently or threateningly, against a place or another group of people

    oai_token-act-pair · gemini-2.0-flash

    storm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    +#+#
    -0.70
    Hentet
    -0.64
    principalColumn
    -0.57
    ophi
    -0.50
    strual
    -0.49
     ***!
    -0.48
    ADATA
    -0.48
    ografi
    -0.47
    ToLeft
    -0.47
    strich
    -0.47
    POSITIVE LOGITS
    thâu
    0.65
    TagHelper
    0.57
     velcro
    0.53
    ambilan
    0.52
     Púb
    0.52
     gepubliceerd
    0.52
     berarti
    0.51
    MethodManager
    0.50
    EndContext
    0.49
    Denied
    0.48
    Activations Density 1.125%

    No Known Activations