© 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. 11745
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people, places, or possessive/associative relationships.

    oai_token-act-pair · gemini-2.0-flash

    locations or geography # This is a best guess

    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
    vener
    -0.46
     pe
    -0.45
    ographiques
    -0.45
    ://"
    -0.45
    webElement
    -0.43
    brigens
    -0.42
    iranje
    -0.42
    UVEN
    -0.40
     }{@
    -0.40
    戚
    -0.40
    POSITIVE LOGITS
     ujednoznacz
    0.66
     الحره
    0.65
    IBarButtonItem
    0.64
    RegressionTest
    0.64
    StoryboardSegue
    0.61
     يتيمه
    0.59
    InputBorder
    0.59
     Agamemnon
    0.58
     Diſ
    0.58
     Efq
    0.56
    Activations Density 1.270%

    No Known Activations