© 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. 15024
    Prev
    Next
    INDEX
    Explanations

    conjunctions and pronouns.

    oai_token-act-pair · gemini-2.0-flash

    the word 'otherwise'

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

    variations of "otherwise"

    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
    MENAFN
    -0.65
    DockStyle
    -0.58
    AutoresizingMask
    -0.56
    ISupport
    -0.56
    Бахар
    -0.55
    UserScript
    -0.54
     FormData
    -0.53
    ImageContext
    -0.53
     intptr
    -0.53
    Insn
    -0.52
    POSITIVE LOGITS
     otherwise
    3.64
    otherwise
    3.19
     Otherwise
    3.02
    Otherwise
    3.00
     OTHERWISE
    2.78
     altrimenti
    2.55
     ellers
    2.23
     sonst
    2.06
     jinak
    1.90
     иначе
    1.89
    Activations Density 4.269%

    No Known Activations