© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3886
    Prev
    Next
    INDEX
    Explanations

    initials or abbreviations following words indicating a person has made a statement, possibly to the press

    oai_token-act-pair · gemini-2.0-flash

    News/quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ########.
    -0.59
     Chwiliwch
    -0.56
    ftagPool
    -0.55
    AndroidJUnit
    -0.54
    providedIn
    -0.52
    ૃ
    -0.52
    rrggbb
    -0.50
     gynnwys
    -0.50
     [*]
    -0.47
    \:
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.82
    AndEndTag
    0.57
     Babu
    0.56
     enrollment
    0.56
     Приступљено
    0.54
    tisgarh
    0.51
    ItemBackground
    0.51
     XCTest
    0.50
    enrollment
    0.50
    StreetMap
    0.50
    Activations Density 7.161%

    No Known Activations