© 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. 10023
    Prev
    Next
    INDEX
    Explanations

    words or short phrases suggesting regulatory change or scientific findings

    oai_token-act-pair · gemini-2.0-flash

    unique, specialized terms in textual data

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

    potential problems/issues

    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
    BeginContext
    -0.49
     betrokken
    -0.47
    TagHelper
    -0.46
     prate
    -0.46
    ="{{$
    -0.45
    =?";
    -0.44
     promise
    -0.44
     içeri
    -0.44
    jména
    -0.42
     Goldie
    -0.42
    POSITIVE LOGITS
    sidemargin
    0.77
     تضيفلها
    0.66
     lenker
    0.65
     незавершена
    0.62
    TintMode
    0.61
     оригіналу
    0.60
    دانشنامهٔ
    0.60
     gynhyrchwyd
    0.57
    InitVars
    0.57
     Peaks
    0.55
    Activations Density 3.210%

    No Known Activations