© 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. 3207
    Prev
    Next
    INDEX
    Explanations

    Objective-C and Swift programming syntax

    oai_token-act-pair · gemini-2.0-flash

    underscore

    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
     _
    -1.55
    (_
    -1.09
     (_
    -1.02
    ._
    -0.87
    ,_
    -0.84
     *_
    -0.84
    )_
    -0.82
    =_
    -0.81
    [_
    -0.76
     [_
    -0.73
    POSITIVE LOGITS
    Kaynakça
    0.59
    Portale
    0.58
    Билгалдахарш
    0.57
    ſelves
    0.56
    তথ্যসূত্র
    0.55
    SEGUIR
    0.55
     itſelf
    0.54
    GEBURTSDATUM
    0.52
    etCode
    0.50
    Eqn
    0.49
    Activations Density 4.830%

    No Known Activations