© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7739
    Prev
    Next
    INDEX
    Explanations

    the word "me" in connection to a number of topics including the self, goals, and dating

    oai_token-act-pair · gemini-2.0-flash

    -ing mental state

    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
     ddelweddau
    -0.64
    AddTagHelper
    -0.64
    AxisAlignment
    -0.60
     Empfang
    -0.59
    AndEndTag
    -0.56
    aarrggbb
    -0.56
     AssemblyProduct
    -0.54
    RetentionPolicy
    -0.53
    instancetype
    -0.52
    ValueStyle
    -0.52
    POSITIVE LOGITS
     hoping
    1.19
     wondering
    1.16
     thinking
    1.14
     wishing
    1.10
     asking
    1.05
     knowing
    1.05
     believing
    1.04
     wanting
    1.03
     trying
    1.02
     claiming
    1.01
    Activations Density 1.801%

    No Known Activations