© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13136
    Prev
    Next
    INDEX
    Explanations

    the pronoun "she".

    oai_token-act-pair · gemini-2.0-flash

    occurrences of 'she' or 'She'

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

    she

    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
     Osborne
    -0.49
     present
    -0.46
     Gate
    -0.42
     Osbourne
    -0.42
    prepareStatement
    -0.41
    jface
    -0.40
    SetWindow
    -0.40
    ━━━━
    -0.40
     deliberate
    -0.39
    碼
    -0.38
    POSITIVE LOGITS
    SerializedName
    0.66
    verwijspagina
    0.65
     Reſ
    0.64
     Houſe
    0.61
    Obrázky
    0.61
     poveznice
    0.60
     houſe
    0.60
     scattata
    0.60
     препратки
    0.59
     Efq
    0.59
    Activations Density 0.327%

    No Known Activations