© 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. 6353
    Prev
    Next
    INDEX
    Explanations

    the word "Inner" or "Inside" and sometimes words related to state boundaries or state revenue agencies

    oai_token-act-pair · gemini-2.0-flash

    inner

    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
     within
    -0.59
     inner
    -0.55
     Within
    -0.54
    inner
    -0.54
     dentro
    -0.52
     WITHIN
    -0.52
    Inner
    -0.51
     Inner
    -0.50
     innermost
    -0.50
     financière
    -0.50
    POSITIVE LOGITS
    MessageTagHelper
    0.92
     NSCoder
    0.85
    новниш
    0.66
    abestanden
    0.65
    KURZBESCHREIBUNG
    0.63
     surla
    0.61
    Diweddarwch
    0.59
     Мексичка
    0.59
    Sucesor
    0.58
    Hochspringen
    0.57
    Activations Density 2.317%

    No Known Activations