© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2558
    Prev
    Next
    INDEX
    Explanations

    mentions of Russia, sanctions, and the US government related to policy and/or law.

    oai_token-act-pair · gemini-2.0-flash

    programming language syntax elements or tokens

    np_token-act-pair-logits · gpt-4o-mini

    political actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     himſelf
    -0.56
     fubject
    -0.53
     neceffary
    -0.52
     reaſon
    -0.51
    iarkan
    -0.50
    arbre
    -0.49
    Sklici
    -0.48
     Cocktail
    -0.48
     poffe
    -0.48
     bougies
    -0.48
    POSITIVE LOGITS
     '\\;'
    0.83
    tagHelperRunner
    0.65
    DoubleQuotes
    0.65
     FontWeight
    0.59
    LayoutStyle
    0.59
    AndroidJUnit
    0.57
     BorderSide
    0.56
     مرئيه
    0.53
    NOPQRST
    0.53
    __(/*!
    0.52
    Activations Density 2.220%

    No Known Activations