© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16148
    Prev
    Next
    INDEX
    Explanations

    the word 'couple' and words and prepositions related to being close to or moving next to something or someone

    oai_token-act-pair · gemini-2.0-flash

    move

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    GEBURTSDATUM
    -0.50
    PhysRevD
    -0.50
    MetaObject
    -0.49
    TagMode
    -0.49
    новниш
    -0.48
    بوابة
    -0.47
    AndEndTag
    -0.46
    toMatch
    -0.46
     Stirn
    -0.44
     زاده
    -0.42
    POSITIVE LOGITS
     move
    2.22
    move
    2.03
     Move
    2.00
     moved
    1.94
     MOVE
    1.87
    Move
    1.84
     moving
    1.74
     moves
    1.73
    moved
    1.71
     Moved
    1.69
    Activations Density 1.472%

    No Known Activations