© 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. 14118
    Prev
    Next
    INDEX
    Explanations

    the characters "Kh" possibly at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'Kh'

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

    Kh

    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
    HA
    -0.50
     ha
    -0.47
    ha
    -0.46
    日至
    -0.44
    ner
    -0.41
    iste
    -0.41
    рок
    -0.41
     hava
    -0.41
     HA
    -0.40
    сте
    -0.40
    POSITIVE LOGITS
    InputBorder
    0.84
     AppCompatTheme
    0.84
    AsUp
    0.81
    EndInit
    0.79
     Савезне
    0.75
    tvguidetime
    0.73
    EndContext
    0.72
     vastaan
    0.71
    TintMode
    0.71
     intptr
    0.71
    Activations Density 0.197%

    No Known Activations