© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6005
    Prev
    Next
    INDEX
    Explanations

    words related to botany and/or religion

    oai_token-act-pair · gemini-2.0-flash

    plant species

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -0.60
     كومونز
    -0.59
     createSlice
    -0.54
    GTCX
    -0.54
    RectangleBorder
    -0.53
    ConstraintMaker
    -0.53
    :✨
    -0.52
    glVertex
    -0.52
    glBegin
    -0.52
    esModule
    -0.52
    POSITIVE LOGITS
    +:+
    0.59
     transfieras
    0.52
    auté
    0.51
    WaitGroup
    0.50
     mắn
    0.50
    RTEE
    0.50
    critical
    0.49
     palmas
    0.47
    æv
    0.47
    acal
    0.46
    Activations Density 0.597%

    No Known Activations