© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3256
    Prev
    Next
    INDEX
    Explanations

    SSH public key authentication details

    oai_token-act-pair · gemini-2.0-flash

    publick

    np_max-act · gemini-2.0-flash

    say "ey" Method used: 2 — because following tokens are predominantly "ey" — say "ey"

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.16
     contenus
    -0.94
     modalités
    -0.90
     Lign
    -0.89
     emplois
    -0.87
    UpInside
    -0.86
    ابل
    -0.85
     obel
    -0.85
     Brack
    -0.85
     Nanda
    -0.84
    POSITIVE LOGITS
    s
    1.19
    oğlu
    1.11
    ed
    1.09
    ی
    1.09
    y
    1.05
    ه
    0.99
    a
    0.98
    ième
    0.94
    er
    0.93
    en
    0.91
    Activations Density 20.067%

    No Known Activations