© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4311
    Prev
    Next
    INDEX
    Explanations

    citations or other references to outside sources

    oai_token-act-pair · gemini-2.0-flash

    et

    np_max-act · gemini-2.0-flash

    say "al" Method used: 2 — because many following tokens are "al"

    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
    ,
    -1.19
    /
    -1.05
     and
    -1.02
     or
    -1.02
     as
    -0.96
     at
    -0.95
     in
    -0.94
     from
    -0.90
     of
    -0.85
     a
    -0.81
    POSITIVE LOGITS
     itſelf
    1.54
     Theſe
    1.48
     Jefus
    1.34
     myſelf
    1.33
     ſmall
    1.30
     photolibrary
    1.30
     ſever
    1.27
     Monfieur
    1.27
     Diſ
    1.25
     pleaſure
    1.25
    Activations Density 2.123%

    No Known Activations