© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15330
    Prev
    Next
    INDEX
    Explanations

    words used to ask questions

    oai_token-act-pair · gemini-2.0-flash

    questions beginning with "how"

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

    how

    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
    
    -0.55
     How
    -0.51
    How
    -0.45
    PathVariable
    -0.41
     how
    -0.41
    Související
    -0.40
     melap
    -0.39
     Is
    -0.38
     andato
    -0.38
     me
    -0.38
    POSITIVE LOGITS
     Czar
    0.75
     AssemblyCulture
    0.74
     Efq
    0.71
     handleMessage
    0.67
     ་་
    0.66
     xenia
    0.65
    Tikang
    0.65
     ABR
    0.64
     HZ
    0.63
     getSystem
    0.63
    Activations Density 0.241%

    No Known Activations