© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7168
    Prev
    Next
    INDEX
    Explanations

    technical terms for operating systems and programming

    oai_token-act-pair · gemini-2.0-flash

    non-english contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Monfieur
    -0.88
    bcryptjs
    -0.85
    دانشنامهٔ
    -0.83
    @[+][
    -0.82
     Majefty
    -0.82
     themſelves
    -0.82
    iastes
    -0.80
     religieuses
    -0.78
     EClass
    -0.77
     quæ
    -0.76
    POSITIVE LOGITS
    Imp
    0.43
    *}
    0.41
     Imp
    0.39
    *}$
    0.38
    ​
    0.38
    ​​
    0.36
    htë
    0.36
     WH
    0.35
     K
    0.35
     utafitiHapana
    0.35
    Activations Density 4.660%

    No Known Activations