© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13631
    Prev
    Next
    INDEX
    Explanations

    the word "himself" or related pronouns

    oai_token-act-pair · gemini-2.0-flash

    himself/themselves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     himself
    -2.59
    himself
    -2.42
     themselves
    -2.36
     herself
    -2.33
     ourselves
    -2.31
    themselves
    -2.28
     Himself
    -2.22
     yourself
    -2.13
     myself
    -2.13
    herself
    -2.09
    POSITIVE LOGITS
    <bos>
    0.84
     समीक्षक
    0.53
    copyOf
    0.50
    aság
    0.50
    ंदीखरीदारी
    0.49
    BeginContext
    0.49
    ’
    0.47
    звание
    0.46
    bedarf
    0.45
    IBOutlet
    0.45
    Activations Density 0.787%

    No Known Activations