© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 712
    Prev
    Next
    INDEX
    Explanations

    code snippets or references to tables and figures

    oai_token-act-pair · gemini-2.0-flash

    tables and menus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Personendaten
    -0.83
    MessageTagHelper
    -0.74
    MODULE
    -0.70
    modelBuilder
    -0.69
     module
    -0.68
    bmod
    -0.68
    moiselle
    -0.67
    tomans
    -0.64
     %=
    -0.64
     modul
    -0.63
    POSITIVE LOGITS
    脚注の使い方
    0.50
    viewDidLoad
    0.46
     trattano
    0.45
    animaux
    0.44
    stdafx
    0.44
     umana
    0.43
    uttosto
    0.43
     mourning
    0.42
    stateProvider
    0.41
     UITextField
    0.40
    Activations Density 2.120%

    No Known Activations