© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10582
    Prev
    Next
    INDEX
    Explanations

    a mix of common words, question phrases, and some punctuation

    oai_token-act-pair · gemini-2.0-flash

    right

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Referencie
    -0.46
    setopt
    -0.44
     cellpadding
    -0.44
    medriver
    -0.43
    iastes
    -0.43
    tagHelperRunner
    -0.42
    BeginContext
    -0.42
    LabelTagHelper
    -0.41
    jsxFileName
    -0.41
     bý
    -0.41
    POSITIVE LOGITS
     right
    2.97
    right
    2.47
    Right
    2.34
     Right
    2.31
     RIGHT
    2.19
    RIGHT
    2.09
     righ
    1.59
    getRight
    1.43
     derecho
    1.37
    righ
    1.37
    Activations Density 5.011%

    No Known Activations