© 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. 11052
    Prev
    Next
    INDEX
    Explanations

    the word "respectively" and sometimes also activates on "ro".

    oai_token-act-pair · gemini-2.0-flash

    respectively

    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
     enfans
    -1.50
     purpoſe
    -1.32
     feroit
    -1.31
     ainfi
    -1.30
     Theſe
    -1.30
     auroit
    -1.30
     Majefty
    -1.29
     Monfieur
    -1.29
     ſeveral
    -1.27
     étoit
    -1.26
    POSITIVE LOGITS
    '
    1.09
     
    1.08
    (
    1.03
    ’
    0.99
    2
    0.98
    -
    0.88
    3
    0.85
    1
    0.84
    0
    0.83
    A
    0.83
    Activations Density 1.654%

    No Known Activations