© 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. 3473
    Prev
    Next
    INDEX
    Explanations

    references to things that have already been said or presented

    oai_token-act-pair · gemini-2.0-flash

    above

    np_max-act · gemini-2.0-flash
    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
     myſelf
    -1.27
    <bos>
    -1.16
     itſelf
    -1.12
     themſelves
    -1.07
     himſelf
    -1.07
     purpoſe
    -1.02
     pleaſure
    -1.01
     Jefus
    -1.01
     Theſe
    -1.01
     Majefty
    -0.98
    POSITIVE LOGITS
    ...
    0.63
    ciaż
    0.56
    …
    0.54
    /
    0.52
    ....
    0.52
     proven
    0.51
    ..
    0.50
     Zacks
    0.49
     =
    0.49
     reag
    0.48
    Activations Density 1.134%

    No Known Activations