© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8859
    Prev
    Next
    INDEX
    Explanations

    the first-person pronoun "I" in various contexts, along with some related verbs and conjunctions.

    oai_token-act-pair · gemini-2.0-flash

    first-person pronouns and speech-related verbs

    np_token-act-pair-logits · gpt-4o-mini

    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_21/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.21.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
    InvalidProtocol
    -0.68
     يتيمه
    -0.68
    Aiheesta
    -0.67
     createSprite
    -0.67
     MyBatis
    -0.66
    
    -0.62
     AssemblyCompany
    -0.62
    μορ
    -0.59
    ScopeManager
    -0.59
    FunctionFlags
    -0.59
    POSITIVE LOGITS
     talked
    0.75
     talks
    0.66
     spoke
    0.66
    <bos>
    0.66
     had
    0.65
     hadn
    0.64
     has
    0.59
     chatted
    0.59
     later
    0.58
     thanked
    0.58
    Activations Density 1.061%

    No Known Activations