© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14751
    Prev
    Next
    INDEX
    Explanations

    instances of the word "course" and phrases that indicate addition or surprise like "even".

    oai_token-act-pair · gemini-2.0-flash

    Commentary, emphasis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    kloped
    -0.60
    ">//
    -0.59
    phazard
    -0.57
     оригіналу
    -0.56
    Obvious
    -0.54
    ernoo
    -0.52
    ilige
    -0.52
    principalTable
    -0.52
    TagHelpers
    -0.50
    󠁢
    -0.50
    POSITIVE LOGITS
     régional
    0.58
     loob
    0.49
     minutter
    0.46
    permitAll
    0.46
     briefly
    0.46
    名为
    0.45
    InSection
    0.44
     marins
    0.44
    Дереккөздер
    0.44
     indipendente
    0.44
    Activations Density 0.204%

    No Known Activations