© 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. 10839
    Prev
    Next
    INDEX
    Explanations

    the word "girl" along with mentions of relatives or injuries

    oai_token-act-pair · gemini-2.0-flash

    girl

    np_max-act · gemini-2.0-flash

    girl

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     girl
    -1.40
     girls
    -1.27
     Girl
    -1.17
    Girl
    -1.07
     Girls
    -1.01
    girl
    -0.99
    girls
    -0.96
     GIRL
    -0.96
     GIRLS
    -0.90
    Girls
    -0.88
    POSITIVE LOGITS
    tvguidetime
    0.86
    Vegeu
    0.74
    tagHelperRunner
    0.73
    __':
    0.70
    最快更新
    0.68
     TextFormField
    0.68
    oprecip
    0.67
     StatelessWidget
    0.66
     EconPapers
    0.63
     budeme
    0.62
    Activations Density 1.367%

    No Known Activations