© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16071
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to names/places, general academic language and medical procedures

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    +#+#
    -0.94
     nahilalakip
    -0.93
    ArgsConstructor
    -0.92
    rungsseite
    -0.92
     препратки
    -0.90
    tagHelperRunner
    -0.89
    setVerticalGroup
    -0.88
    ⓧ
    -0.86
    AsUp
    -0.82
     Wiktionnaire
    -0.82
    POSITIVE LOGITS
    PMailer
    0.44
    便宜
    0.40
     -
    0.36
    or
    0.36
     (
    0.35
     ta
    0.35
    umb
    0.35
    i
    0.34
     w
    0.34
    kách
    0.34
    Activations Density 20.226%

    No Known Activations