© 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. 5667
    Prev
    Next
    INDEX
    Explanations

    words relating to actions, requests, or providing/exchanging information

    oai_token-act-pair · gemini-2.0-flash

    personal information

    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
     المعيارى
    -0.58
     AssemblyCulture
    -0.57
    ngdoc
    -0.53
     Italijani
    -0.51
     FetchType
    -0.51
     consultato
    -0.50
    GOTREF
    -0.49
    :+:
    -0.48
    eload
    -0.47
     ['./
    -0.47
    POSITIVE LOGITS
     themſelves
    0.63
     Monfieur
    0.61
     auffi
    0.58
     Theſe
    0.57
     Wikidata
    0.57
     Jefus
    0.56
     purpoſe
    0.56
    dotenv
    0.56
     responseData
    0.55
     Beſ
    0.54
    Activations Density 7.774%

    No Known Activations