© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13889
    Prev
    Next
    INDEX
    Explanations

    seemingly random special characters and control characters.

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tagHelperRunner
    -0.80
    RenderAtEndOf
    -0.72
     Majefty
    -0.71
    ConstraintMaker
    -0.71
     дописавши
    -0.68
     Theſe
    -0.68
     Diſ
    -0.66
     Roskov
    -0.65
     Anſ
    -0.65
    WriteTagHelper
    -0.65
    POSITIVE LOGITS
    ไหม
    0.49
     megfe
    0.49
    сього
    0.47
     kapcsol
    0.47
    นะคะ
    0.46
    บ้าง
    0.46
    อร่อย
    0.45
    ​
    0.45
     I
    0.45
    นะครับ
    0.45
    Activations Density 1.346%

    No Known Activations