© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10989
    Prev
    Next
    INDEX
    Explanations

    the word 'return(s)'

    oai_token-act-pair · gemini-2.0-flash

    returns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     return
    -0.92
     
    -0.84
     “
    -0.74
     former
    -0.72
     and
    -0.72
    ,
    -0.70
     is
    -0.66
     or
    -0.66
     ‘
    -0.66
    <strong>
    -0.65
    POSITIVE LOGITS
    دانشنامهٔ
    1.33
     Baillargeon
    1.28
     ainfi
    1.24
     iſt
    1.16
     myſelf
    1.14
     auroit
    1.13
     صوتيه
    1.10
     uſed
    1.10
     doubtnut
    1.09
     feroit
    1.09
    Activations Density 0.681%

    No Known Activations