© 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. 2270
    Prev
    Next
    INDEX
    Explanations

    words probably related to political leanings or affiliations, especially communism and leninism, along with related terminology.

    oai_token-act-pair · gemini-2.0-flash

    words with specific prefixes or linguistic structures

    np_token-act-pair-logits · gpt-4o-mini
    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
     Timor
    -0.42
     fixed
    -0.40
     far
    -0.40
    gob
    -0.39
     Cal
    -0.39
     la
    -0.39
     Kid
    -0.38
    ど
    -0.38
     Douglas
    -0.38
    gettime
    -0.38
    POSITIVE LOGITS
    Geplaatst
    1.00
     EconPapers
    0.92
     Monfieur
    0.84
    IntoConstraints
    0.84
     Majefty
    0.84
     ProtoMessage
    0.84
     pleaſure
    0.82
     purpoſe
    0.81
    AnchorStyles
    0.81
     propOrder
    0.81
    Activations Density 0.333%

    No Known Activations