© 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. 14730
    Prev
    Next
    INDEX
    Explanations

    mathematical theorems, corollaries, and propositions

    oai_token-act-pair · gemini-2.0-flash

    reference terms and mathematical constructs

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

    Math and Latex formatting

    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
    GetAxis
    -0.49
    utus
    -0.45
     blanco
    -0.44
     II
    -0.42
    oten
    -0.41
    phinx
    -0.41
    исленность
    -0.41
    II
    -0.41
    fit
    -0.40
    Demikian
    -0.39
    POSITIVE LOGITS
     متعلقه
    0.90
    IVEREF
    0.84
    AndEndTag
    0.84
    windowFixed
    0.83
    MENAFN
    0.81
    ValueStyle
    0.78
     disambiguazione
    0.77
    WebVitals
    0.74
    AndroidJUnit
    0.73
     محفوظة
    0.70
    Activations Density 3.636%

    No Known Activations