© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14139
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to dates, time periods, and historical events

    oai_token-act-pair · gemini-2.0-flash

    migration of people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    +#+#
    -0.94
     beginnetje
    -0.71
    MethodManager
    -0.67
    ikala
    -0.61
     defaultstate
    -0.60
    ValueStyle
    -0.59
    InputTagHelper
    -0.57
    OGND
    -0.57
     Vikipedi
    -0.56
    AndEndTag
    -0.56
    POSITIVE LOGITS
    ძ
    0.43
     spelt
    0.42
    Lebens
    0.42
    受益
    0.41
     podí
    0.41
    mtrl
    0.40
     CommonModule
    0.40
     invol
    0.40
     nisso
    0.40
     whims
    0.39
    Activations Density 4.857%

    No Known Activations