© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14402
    Prev
    Next
    INDEX
    Explanations

    a variety of words associated with positive or negative emotional intensity

    oai_token-act-pair · gemini-2.0-flash

    descriptive writing

    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
    ).
    -0.47
    ),
    -0.40
    )-
    -0.40
     tarafından
    -0.39
    ;
    -0.39
    )
    -0.39
    !
    -0.38
    setOnItem
    -0.38
    4
    -0.37
     eller
    -0.37
    POSITIVE LOGITS
    elemField
    0.99
    LookAnd
    0.95
     resourceCulture
    0.93
    saraba
    0.91
    MLLoader
    0.89
     صوتيه
    0.89
    rungsseite
    0.87
     Roskov
    0.86
    contentLoaded
    0.86
    tagHelperRunner
    0.84
    Activations Density 11.174%

    No Known Activations