© 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. 15070
    Prev
    Next
    INDEX
    Explanations

    discussions about fixing mechanical or plumbing problems

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terms

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

    technical instructions

    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
    ums
    -0.44
     gre
    -0.43
    bra
    -0.43
     of
    -0.41
    org
    -0.41
    agent
    -0.41
    永
    -0.41
     tecnologia
    -0.41
    cole
    -0.41
     طرف
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.88
    RenderAtEndOf
    0.84
     архивлан
    0.81
     CreateTagHelper
    0.81
    IUrlHelper
    0.78
     Administrativna
    0.77
     Efq
    0.73
     оригіналу
    0.71
     }}"></
    0.69
     crdi
    0.69
    Activations Density 4.525%

    No Known Activations