© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10137
    Prev
    Next
    INDEX
    Explanations

    file paths

    oai_token-act-pair · gemini-2.0-flash

    :\

    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
     double
    -0.60
     a
    -0.59
     at
    -0.59
     to
    -0.57
     char
    -0.57
     for
    -0.56
     is
    -0.56
     he
    -0.54
     pra
    -0.54
     me
    -0.53
    POSITIVE LOGITS
     purpoſe
    1.16
     kasarigan
    1.10
     raiſ
    1.05
     myſelf
    1.03
     EconPapers
    1.00
     uſe
    0.99
     itſelf
    0.98
    RenderAtEndOf
    0.97
     faſt
    0.96
     themſelves
    0.95
    Activations Density 1.008%

    No Known Activations