© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13605
    Prev
    Next
    INDEX
    Explanations

    references to people being in or on a bed

    oai_token-act-pair · gemini-2.0-flash

    bed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     bed
    -2.55
    Bed
    -2.34
     Bed
    -2.34
    bed
    -2.33
     beds
    -2.22
     BED
    -2.16
    BED
    -2.09
     Beds
    -2.06
    beds
    -2.03
     sleep
    -1.82
    POSITIVE LOGITS
    Ikus
    0.49
    뀔
    0.43
    golang
    0.43
    laat
    0.40
    뀜
    0.40
     بتاريخ
    0.39
    huit
    0.39
    Mucho
    0.38
     Tau
    0.37
     collè
    0.37
    Activations Density 0.973%

    No Known Activations