© 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. 8777
    Prev
    Next
    INDEX
    Explanations

    words representing titles, organizations, and personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    article 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
    SourceChecksum
    -0.59
     PublicKey
    -0.48
    Dichloroethene
    -0.47
    leting
    -0.47
    cines
    -0.47
    nitzel
    -0.46
    Came
    -0.44
     @"/
    -0.41
    )|\
    -0.41
    Linki
    -0.41
    POSITIVE LOGITS
    thâu
    0.77
     auffi
    0.69
     Jefus
    0.68
     Majefty
    0.68
     shares
    0.66
     Monfieur
    0.64
     Houſe
    0.64
     Shares
    0.62
     Conſ
    0.60
     houſe
    0.59
    Activations Density 11.993%

    No Known Activations