© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1263
    Prev
    Next
    INDEX
    Explanations

    the use of auxiliary verbs such as, will, was, should, are, and similar words

    oai_token-act-pair · gemini-2.0-flash

    fight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ↵↵
    -3.38
    ↵
    -2.61
    <eos>
    -2.42
    ↵↵↵
    -1.91
    ↵↵↵↵
    -1.80
    ↵↵↵↵↵
    -1.57
    ↵↵↵↵↵↵
    -1.55
    ↵↵↵↵↵↵↵↵
    -1.45
    ↵↵↵↵↵↵↵
    -1.45
     ...
    -1.37
    POSITIVE LOGITS
     BorderSide
    0.54
     }}$}
    0.54
     }(\
    0.54
    囗
    0.49
     createSprite
    0.48
     }(
    0.48
    >(_
    0.44
    tagHelperRunner
    0.43
     }{
    0.43
    ']->
    0.42
    Activations Density 6.226%

    No Known Activations