© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7429
    Prev
    Next
    INDEX
    Explanations

    the first-person pronoun "I" and related words like "me" or "my", sometimes also picking up the verb tense of "to be"

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    OGND
    -0.48
     Administrativna
    -0.46
     Commencez
    -0.46
    iconque
    -0.46
     kill
    -0.45
     root
    -0.44
    دانشنامهٔ
    -0.44
     Root
    -0.44
     برس
    -0.43
    protoimpl
    -0.42
    POSITIVE LOGITS
    AnchorStyles
    0.73
     StatelessWidget
    0.72
     onOptions
    0.65
    __(/*!
    0.62
    __["
    0.60
    ChildScrollView
    0.59
    VersionUID
    0.58
     Uru
    0.58
    CloseOperation
    0.53
    GIVEREF
    0.52
    Activations Density 1.146%

    No Known Activations