© 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. 12666
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words, usually nouns, with some positive or negative connotation, within a sentence.

    oai_token-act-pair · gemini-2.0-flash

    common words

    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
     GenerationType
    -0.83
    GEBURTSDATUM
    -0.79
    findpost
    -0.77
     ContentValues
    -0.76
    OGND
    -0.76
     дописавши
    -0.73
    KommentareTeilen
    -0.70
    ]--;
    -0.70
    setVerticalGroup
    -0.68
     sumpay
    -0.68
    POSITIVE LOGITS
     vairāk
    0.47
    documentElement
    0.46
    ikke
    0.43
     lī
    0.42
    一一
    0.42
    <
    0.39
    anty
    0.39
     I
    0.39
    全局
    0.39
    نيف
    0.39
    Activations Density 17.672%

    No Known Activations