© 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. 7829
    Prev
    Next
    INDEX
    Explanations

    a combination of location or people's names, short words, titles of media articles, and numbers that might be dates

    oai_token-act-pair · gemini-2.0-flash

    Journalism and publications

    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
    providedIn
    -0.60
    MigrationBuilder
    -0.60
    ]^{-
    -0.53
    OrNil
    -0.51
     invokingState
    -0.51
    (!__
    -0.48
    PreferredItem
    -0.47
    __((
    -0.46
    Datuak
    -0.45
     ioutil
    -0.44
    POSITIVE LOGITS
     EconPapers
    0.53
     typelib
    0.49
    jokes
    0.49
     Debates
    0.49
    Opinions
    0.48
     Journalists
    0.48
    Writers
    0.48
     Jokes
    0.48
     Examiners
    0.47
    conspiracy
    0.47
    Activations Density 18.404%

    No Known Activations