© 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. 7766
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters used in various contexts such as currency, math, bullets, and lists.

    oai_token-act-pair · gemini-2.0-flash

    !!!

    np_max-act-logits · gemini-2.0-flash

    words containing "ſ" (long s)

    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
    findpost
    -0.96
    IUrlHelper
    -0.91
    UrlResolution
    -0.71
     Exacts
    -0.69
    roides
    -0.68
    FunctionFlags
    -0.64
    المناصب
    -0.63
    ACIONAL
    -0.62
     mergeFrom
    -0.61
    ImageContext
    -0.61
    POSITIVE LOGITS
     ſtre
    0.59
     Theſe
    0.58
     houſe
    0.58
     Jefus
    0.58
    ſelf
    0.55
     Majefty
    0.53
     myſelf
    0.51
     ―――――
    0.50
    '".
    0.50
     muſt
    0.50
    Activations Density 29.951%

    No Known Activations