© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14907
    Prev
    Next
    INDEX
    Explanations

    text from scientific reports that discusses soil samples, environmental warming and biomass

    oai_token-act-pair · gemini-2.0-flash

    terms related to environmental science

    np_token-act-pair-logits · gpt-4o-mini

    Organic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ftagPool
    -0.81
    StructEnd
    -0.77
    DockStyle
    -0.75
    OCCURRED
    -0.71
     purpoſe
    -0.69
    principalTable
    -0.69
     myſelf
    -0.69
     ſtate
    -0.68
     itſelf
    -0.65
     reaſon
    -0.65
    POSITIVE LOGITS
    Litter
    0.50
    litter
    0.50
    bigg
    0.50
    Personensuche
    0.49
     instanceof
    0.48
     Organic
    0.47
    FormField
    0.47
     organic
    0.47
     corporate
    0.46
    heureusement
    0.46
    Activations Density 1.611%

    No Known Activations