© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4425
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "to sit" as well as related concepts like communication and minor medical issues.

    oai_token-act-pair · gemini-2.0-flash

    sat/met

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     &___
    -0.84
    mặt
    -0.76
    ESOME
    -0.73
    ఔ
    -0.71
    ]),
    -0.71
     "..\..\..\
    -0.69
    IMUM
    -0.68
    parsedMessage
    -0.66
    pecially
    -0.66
    aringan
    -0.66
    POSITIVE LOGITS
     Tarzan
    0.69
    '
    0.65
    moveToFirst
    0.65
    Access
    0.60
    <bos>
    0.60
     Dhabi
    0.58
    "
    0.57
     Rizal
    0.57
    دانشنامهٔ
    0.57
    1
    0.55
    Activations Density 1.575%

    No Known Activations