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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15706
    Prev
    Next
    INDEX
    Explanations

    advice related to medicines and scientific studies

    oai_token-act-pair · gemini-2.0-flash

    drugs and medicine

    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
     compound
    -1.01
    compound
    -0.89
     Compound
    -0.88
    Compound
    -0.85
     COMPOUND
    -0.85
    +#+#
    -0.81
     materials
    -0.73
     drug
    -0.72
     Materials
    -0.69
    materials
    -0.68
    POSITIVE LOGITS
    @[+][
    0.58
    terase
    0.53
    peur
    0.51
     getopt
    0.49
    UnitTesting
    0.48
     defaultstate
    0.47
     squads
    0.45
    новништво
    0.45
    hrungen
    0.45
     AssemblyVersion
    0.45
    Activations Density 3.839%

    No Known Activations