© 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. 12910
    Prev
    Next
    INDEX
    Explanations

    words related to thinking, explaining, asking, opining and emotional reaction to things.

    oai_token-act-pair · gemini-2.0-flash

    The ending -ing

    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
    ypeł
    -0.52
    rupal
    -0.50
    Sever
    -0.50
    äs
    -0.49
    vin
    -0.48
    ptime
    -0.47
    чеб
    -0.47
    tin
    -0.47
     Racine
    -0.47
    ysen
    -0.46
    POSITIVE LOGITS
    ings
    1.06
    ers
    0.98
     ing
    0.94
    ingly
    0.92
    Ing
    0.92
    inge
    0.89
    ingt
    0.78
    INGS
    0.77
    Билгалдахарш
    0.77
    inga
    0.76
    Activations Density 2.747%

    No Known Activations