© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6301
    Prev
    Next
    INDEX
    Explanations

    things that are unique identifiers such as dates, legislation titles, monetary amounts, personal pronouns, company names

    oai_token-act-pair · gemini-2.0-flash

    legal references

    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
     perſon
    -0.58
     raiſ
    -0.56
     becauſe
    -0.56
     ſhould
    -0.53
     purpoſe
    -0.53
     '\\;'
    -0.52
     uſ
    -0.52
     uſed
    -0.52
     whoſe
    -0.52
     juſ
    -0.51
    POSITIVE LOGITS
    ViewFeatures
    0.58
    NTIS
    0.56
    UNDP
    0.49
    ISPR
    0.49
    elab
    0.48
    IPAC
    0.48
    ACGIH
    0.48
    INSEE
    0.47
    Affiliation
    0.47
    RICO
    0.47
    Activations Density 15.399%

    No Known Activations