© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10654
    Prev
    Next
    INDEX
    Explanations

    strings of numbers and letters separated by hyphens

    oai_token-act-pair · gemini-2.0-flash

    tokens ending in specific letters or patterns

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

    4

    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
     Roskov
    -1.12
    AndEndTag
    -1.00
    IUrlHelper
    -0.96
    IVEREF
    -0.96
    MLLoader
    -0.93
     صوتيه
    -0.91
     beginnetje
    -0.90
    ьаж
    -0.89
    InitVars
    -0.88
    PullParser
    -0.87
    POSITIVE LOGITS
    ly
    0.55
    o
    0.54
    s
    0.54
    sc
    0.53
    y
    0.51
     
    0.51
    com
    0.50
    end
    0.50
    b
    0.48
    1
    0.48
    Activations Density 1.561%

    No Known Activations