© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4225
    Prev
    Next
    INDEX
    Explanations

    hexadecimal byte code sequences

    oai_token-act-pair · gemini-2.0-flash

    code and hexadecimals

    np_max-act-logits · gemini-2.0-flash

    say "d or e"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Ｄ
    -0.70
    D
    -0.63
     Де
    -0.59
     Դ
    -0.55
     De
    -0.55
    𝐷
    -0.54
     Д
    -0.54
     D
    -0.53
    Dt
    -0.52
     Ді
    -0.51
    POSITIVE LOGITS
     propOrder
    0.88
     d
    0.84
     nahilalakip
    0.77
     dei
    0.77
     da
    0.77
     de
    0.75
     snippetHide
    0.75
    ԁ
    0.74
     dey
    0.73
     del
    0.72
    Activations Density 15.532%

    No Known Activations