© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12087
    Prev
    Next
    INDEX
    Explanations

    filler words and short grammatical words

    oai_token-act-pair · gemini-2.0-flash

    Tattoo

    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
    +#+
    -0.69
    MigrationBuilder
    -0.68
     مرئيه
    -0.65
     يتيمه
    -0.63
    RegistryLite
    -0.62
     дописавши
    -0.60
     eenige
    -0.59
    WindowListener
    -0.57
    ContentAsync
    -0.56
     Audiodateien
    -0.56
    POSITIVE LOGITS
     body
    0.90
     ink
    0.75
     Body
    0.75
    Body
    0.73
    body
    0.73
     Permanent
    0.62
     Ink
    0.60
     Körpers
    0.60
     BODY
    0.59
     permanent
    0.59
    Activations Density 1.009%

    No Known Activations