© 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. 4185
    Prev
    Next
    INDEX
    Explanations

    verbs related to something happening or having happened

    oai_token-act-pair · gemini-2.0-flash

    Outcomes and states of being

    np_max-act · gemini-2.0-flash

    ed

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    -1.22
     decidieron
    -1.05
     furent
    -1.02
     avoient
    -1.01
     Мексичка
    -1.01
     Majefty
    -1.01
     ordenó
    -1.00
     wept
    -0.98
    ^(@)
    -0.98
     disappeared
    -0.96
    POSITIVE LOGITS
    ↵↵
    1.12
     
    1.01
     a
    0.96
     the
    0.93
     to
    0.84
    ↵
    0.84
     some
    0.76
     an
    0.75
    ded
    0.75
     “
    0.75
    Activations Density 2.425%

    No Known Activations