© 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. 7072
    Prev
    Next
    INDEX
    Explanations

    language indicating a software release or update

    oai_token-act-pair · gemini-2.0-flash

    words related to significant changes or updates

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

    significant

    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
    <?
    -0.52
    Viki
    -0.49
    ccoli
    -0.46
    ็ง
    -0.46
    /**
    -0.45
    Put
    -0.44
    #
    -0.43
    ́i
    -0.42
    izare
    -0.42
    Estar
    -0.41
    POSITIVE LOGITS
     significant
    1.24
    significant
    1.18
     substantial
    1.12
    Significant
    1.09
     Significant
    1.08
     major
    1.03
    substantial
    0.99
     SIGNIFIC
    0.99
     Substantial
    0.98
     CreateTagHelper
    0.93
    Activations Density 4.740%

    No Known Activations