© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5434
    Prev
    Next
    INDEX
    Explanations

    references to fingers or something being "at your"

    oai_token-act-pair · gemini-2.0-flash

    words related to fingers

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

    finger

    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
     Hands
    -0.60
    hands
    -0.60
     мәкал
    -0.60
     hands
    -0.59
     mãos
    -0.50
    Hands
    -0.49
    躇
    -0.48
     handen
    -0.47
     braccia
    -0.47
     rispet
    -0.45
    POSITIVE LOGITS
     finger
    1.53
    finger
    1.29
     Finger
    1.27
     fingers
    1.27
    Finger
    1.14
    fingers
    0.96
     fing
    0.96
     Fingers
    0.92
     doigt
    0.87
     dedo
    0.82
    Activations Density 1.665%

    No Known Activations