© 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. 11818
    Prev
    Next
    INDEX
    Explanations

    the word 'trim' and sometimes the word 'target'

    oai_token-act-pair · gemini-2.0-flash

    trim

    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
     Efq
    -1.04
     myſelf
    -1.01
     purpoſe
    -1.01
     ſever
    -0.98
     Monfieur
    -0.96
     Jefus
    -0.96
     ainfi
    -0.95
     ſta
    -0.94
     Houſe
    -0.94
     Anſ
    -0.93
    POSITIVE LOGITS
    发表于
    0.66
    RegistryLite
    0.57
     not
    0.54
     is
    0.53
     F
    0.52
     I
    0.52
     He
    0.52
    '
    0.51
     or
    0.51
    ↵↵
    0.50
    Activations Density 0.441%

    No Known Activations