© 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. 8451
    Prev
    Next
    INDEX
    Explanations

    the word "touch" or its variations along with words related to grasping ideas or concepts.

    oai_token-act-pair · gemini-2.0-flash

    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
    ViewFeatures
    -1.13
    IntoConstraints
    -0.98
    IndentedString
    -0.88
    EDEFAULT
    -0.85
    expandindo
    -0.85
    Personensuche
    -0.84
    PreferredItem
    -0.84
    WithIOException
    -0.84
    цездатний
    -0.84
    ValueStyle
    -0.83
    POSITIVE LOGITS
     a
    0.57
     Go
    0.47
     go
    0.47
     gran
    0.45
     out
    0.44
     co
    0.44
    HomeAsUpEnabled
    0.44
     base
    0.43
     sen
    0.43
     valid
    0.43
    Activations Density 7.163%

    No Known Activations