© 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. 14606
    Prev
    Next
    INDEX
    Explanations

    words and phrases dealing with how people are seen in relation to each other, or how components are viewed as a single entity

    oai_token-act-pair · gemini-2.0-flash

    legal and business contexts

    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
    ORETICAL
    -0.46
     以
    -0.41
     base
    -0.39
    base
    -0.39
     sk
    -0.39
     خلا
    -0.39
    ΗΣ
    -0.38
    /**
    -0.38
    ...
    -0.38
    ce
    -0.38
    POSITIVE LOGITS
    webElementXpaths
    1.00
    UnsafeEnabled
    0.87
    ########.
    0.77
    +:+
    0.76
     Normdatei
    0.76
    MemoryWarning
    0.76
    matchCondition
    0.75
    tvguidetime
    0.73
    Personensuche
    0.73
     Италијани
    0.73
    Activations Density 2.293%

    No Known Activations