© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4139
    Prev
    Next
    INDEX
    Explanations

    words and short phrases about consumer products, software, and online commerce

    oai_token-act-pair · gemini-2.0-flash

    computer software, advertisements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     صوتيه
    -0.79
    <bos>
    -0.61
     Normdatei
    -0.57
     gynhyrchwyd
    -0.57
    tagHelperRunner
    -0.57
    IsContent
    -0.56
    Diweddarwch
    -0.56
    üyada
    -0.56
     pleaſure
    -0.52
     Bourgoin
    -0.51
    POSITIVE LOGITS
    herin
    0.59
    iterranean
    0.58
     tslint
    0.57
    θεν
    0.57
    줌
    0.55
    oteric
    0.55
    ipedi
    0.53
     bcrypt
    0.53
    OOTDTY
    0.53
    polated
    0.52
    Activations Density 0.684%

    No Known Activations