© 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. 7834
    Prev
    Next
    INDEX
    Explanations

    Arabic letters or script and some symbols

    oai_token-act-pair · gemini-2.0-flash

    Selection and preference terms in Arabic

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

    Code snippets

    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
    WebControls
    -0.88
     ProtoMessage
    -0.87
     pinulongan
    -0.86
     AssemblyCompany
    -0.85
     مشين
    -0.84
    MessageOf
    -0.84
    MigrationBuilder
    -0.83
    principalColumn
    -0.82
    httphttps
    -0.81
     surla
    -0.80
    POSITIVE LOGITS
     the
    0.47
     sprá
    0.35
     žaid
    0.32
    IGENCE
    0.31
    tip
    0.30
     Fine
    0.30
    ="#"><
    0.30
     الش
    0.29
     την
    0.28
    Fine
    0.28
    Activations Density 1.582%

    No Known Activations