© 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. 15064
    Prev
    Next
    INDEX
    Explanations

    positive words related to improvement or a desired result

    oai_token-act-pair · gemini-2.0-flash

    enhancement, power

    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
     Савезне
    -0.59
    Distances
    -0.53
    DebuggerNonUser
    -0.47
     viewType
    -0.45
    Visión
    -0.43
    anstalt
    -0.41
     الا
    -0.40
    Kön
    -0.40
    أس
    -0.40
    าส
    -0.39
    POSITIVE LOGITS
     فريبيس
    0.73
    rosin
    0.68
    AsUp
    0.67
     firepower
    0.65
    Демографія
    0.64
    Personensuche
    0.63
     potr
    0.63
    BlockingQueue
    0.62
     sustained
    0.62
    __':
    0.60
    Activations Density 2.832%

    No Known Activations