© 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. 11169
    Prev
    Next
    INDEX
    Explanations

    words or abbreviation strings that are capitalized and short and may represent categories or acronyms

    oai_token-act-pair · 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
    <bos>
    -1.27
    InjectAttribute
    -0.65
    tagHelperRunner
    -0.59
    __))
    -0.58
    LookAnd
    -0.55
    MessageOf
    -0.55
    ])),
    -0.51
    BeginContext
    -0.49
     where
    -0.48
    ⓧ
    -0.47
    POSITIVE LOGITS
    PyExc
    0.69
     للمعارف
    0.67
    ethene
    0.63
    gdx
    0.59
     كورة
    0.58
     photolibrary
    0.57
    openqa
    0.57
    destroyAll
    0.57
    chanical
    0.56
     Thebes
    0.56
    Activations Density 10.839%

    No Known Activations