© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11839
    Prev
    Next
    INDEX
    Explanations

    instances of a person's difficulty in finding a solution

    oai_token-act-pair · gemini-2.0-flash

    solutions

    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
    öglichkeiten
    -0.77
    impossible
    -0.75
     للمعارف
    -0.73
    ########.
    -0.71
    +#+#
    -0.71
    angeran
    -0.71
     sulit
    -0.70
    RemoteException
    -0.69
     attempts
    -0.68
     Attempts
    -0.68
    POSITIVE LOGITS
    անդ
    0.42
     tùy
    0.42
    おきます
    0.40
     muut
    0.39
    ädie
    0.38
    逗
    0.37
     niks
    0.37
    点头
    0.37
    IsPostBack
    0.37
    OON
    0.36
    Activations Density 1.223%

    No Known Activations