© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3153
    Prev
    Next
    INDEX
    Explanations

    phrases of comparison or statements of relative degree.

    oai_token-act-pair · gemini-2.0-flash

    related to "touch"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Majefty
    -1.04
     ſeveral
    -1.03
     ſever
    -1.00
     houſe
    -0.99
     pleaſure
    -0.97
     Jefus
    -0.96
     myſelf
    -0.95
     fevere
    -0.94
     ſtate
    -0.92
     fubject
    -0.92
    POSITIVE LOGITS
     touched
    0.65
     ever
    0.58
     even
    0.58
     touching
    0.56
     touch
    0.56
    touched
    0.53
     dent
    0.52
    тро
    0.50
     b
    0.49
     Tou
    0.49
    Activations Density 2.207%

    No Known Activations