© 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. 3340
    Prev
    Next
    INDEX
    Explanations

    the phrases "in the", numbers separated by hyphens and commas, and the word "while"

    oai_token-act-pair · gemini-2.0-flash

    unique or formatted words

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

    foreign words

    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
     GenerationType
    -0.72
    IUrlHelper
    -0.71
    はじめに
    -0.68
    MigrationBuilder
    -0.67
    AnchorStyles
    -0.67
    RenderAtEndOf
    -0.66
    athyroid
    -0.64
    ]")]
    -0.63
    קישורים
    -0.61
    LookAnd
    -0.59
    POSITIVE LOGITS
    Tembelea
    0.50
     marié
    0.44
    mäs
    0.44
     kommunen
    0.43
     masculinos
    0.41
     suaminya
    0.41
     toalha
    0.40
     Demographics
    0.40
     eorum
    0.39
    getragen
    0.39
    Activations Density 0.164%

    No Known Activations