© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10598
    Prev
    Next
    INDEX
    Explanations

    titles of books and anthology series

    oai_token-act-pair · gemini-2.0-flash

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     his
    -0.50
     the
    -0.50
     with
    -0.47
     its
    -0.46
    يميديا
    -0.45
     nothing
    -0.45
     whilst
    -0.44
     de
    -0.44
     pairs
    -0.44
     into
    -0.43
    POSITIVE LOGITS
    RunAsync
    0.84
    StoryboardSegue
    0.74
    MemoryWarning
    0.71
     propOrder
    0.70
    CastException
    0.67
     referenties
    0.67
    ագրություններ
    0.66
    ChildScrollView
    0.66
    انجليز
    0.66
    Enllaces
    0.66
    Activations Density 0.731%

    No Known Activations