© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 4654
    Prev
    Next
    INDEX
    Explanations

    strings in python code that are using .format to substitute a variable in the string

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RuleContext
    -0.96
    TagMode
    -0.95
     ExecuteAsync
    -0.90
    tagHelperRunner
    -0.85
    SequentialGroup
    -0.85
    GEBURTSDATUM
    -0.83
    webElementXpaths
    -0.81
     CreateTagHelper
    -0.81
    ArgsConstructor
    -0.79
    rungsseite
    -0.79
    POSITIVE LOGITS
    and
    0.40
    of
    0.37
    to
    0.37
    form
    0.37
    uf
    0.37
    ảng
    0.36
    OF
    0.36
     fiind
    0.36
    l
    0.36
    ti
    0.35
    Activations Density 0.625%

    No Known Activations