© 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. 9406
    Prev
    Next
    INDEX
    Explanations

    emoticons and colons

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    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
    +#+#
    -0.65
    ContentAsync
    -0.65
    ahuje
    -0.59
    Tembelea
    -0.52
    TestTools
    -0.52
     للاسماء
    -0.49
    ագրություններ
    -0.49
    #
    -0.48
    HomeAsUpEnabled
    -0.47
     springfox
    -0.47
    POSITIVE LOGITS
     محفوظة
    0.66
    noons
    0.58
     consultato
    0.55
    GEBURTS
    0.52
    schaft
    0.50
     JADX
    0.50
    words
    0.47
    genstein
    0.47
     getApplication
    0.47
    ScopeManager
    0.46
    Activations Density 0.820%

    No Known Activations