© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4337
    Prev
    Next
    INDEX
    Explanations

    words related to construction and addresses

    oai_token-act-pair · gemini-2.0-flash

    water related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    +#+
    -0.69
     Wiktionnaire
    -0.68
     '{@
    -0.66
    endphp
    -0.63
    #
    -0.61
    !*\
    -0.60
    MethodImpl
    -0.59
    makeText
    -0.58
     оригіналу
    -0.57
     Juliette
    -0.57
    POSITIVE LOGITS
     water
    0.82
     puddle
    0.75
     puddles
    0.74
    water
    0.73
    水
    0.73
     drain
    0.69
    Water
    0.68
     rainwater
    0.67
     Water
    0.66
     drainage
    0.63
    Activations Density 0.781%

    No Known Activations