© 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. 8955
    Prev
    Next
    INDEX
    Explanations

    C# programming code syntax

    oai_token-act-pair · gemini-2.0-flash

    words starting with special characters or uncommon letters

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

    C# code

    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
     [
    -0.80
     K
    -0.70
     m
    -0.69
     et
    -0.66
     he
    -0.65
     me
    -0.65
     di
    -0.65
     I
    -0.65
     A
    -0.64
     ve
    -0.64
    POSITIVE LOGITS
     Majefty
    1.25
     Efq
    1.20
     Houſe
    1.17
     ―――――
    1.16
    ſelf
    1.16
     itſelf
    1.14
     Jefus
    1.12
     Diſ
    1.10
     Anſ
    1.05
     Eſ
    1.05
    Activations Density 1.771%

    No Known Activations