© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14195
    Prev
    Next
    INDEX
    Explanations

    adverbs and words related to patterns or routine

    oai_token-act-pair · gemini-2.0-flash

    adverbs of frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     itſelf
    -0.83
     يتيمه
    -0.78
    +#+#
    -0.73
     purpoſe
    -0.72
     poffible
    -0.69
    ſelf
    -0.68
     leſs
    -0.67
     للمعارف
    -0.66
     kasarigan
    -0.66
    ſelves
    -0.65
    POSITIVE LOGITS
     bef
    0.47
     also
    0.47
    InitVars
    0.46
    queryInterface
    0.46
    ByName
    0.46
     multiple
    0.45
    daging
    0.45
     name
    0.44
     Multiple
    0.44
    cosine
    0.43
    Activations Density 0.324%

    No Known Activations