© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12055
    Prev
    Next
    INDEX
    Explanations

    words related to force and control, including actual power and state power, but also things like words and magic being powerful.

    oai_token-act-pair · gemini-2.0-flash

    power

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    }")
    -0.61
    BeginContext
    -0.55
    tidine
    -0.54
    prepareStatement
    -0.49
     stanovnika
    -0.48
     scand
    -0.48
     Payable
    -0.48
    NewReader
    -0.47
    zwe
    -0.47
     Suivez
    -0.47
    POSITIVE LOGITS
     base
    0.61
    ieteur
    0.60
    Autoritní
    0.60
     snippetHide
    0.55
     Base
    0.55
    yarnpkg
    0.52
     Biôgrafia
    0.50
    uxxxx
    0.49
    base
    0.49
    WriteTagHelper
    0.48
    Activations Density 4.565%

    No Known Activations