© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11879
    Prev
    Next
    INDEX
    Explanations

    occurrences of the string "idx" or "Index" in code

    oai_token-act-pair · gemini-2.0-flash

    idx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -1.20
     houſe
    -1.14
     itſelf
    -1.13
     Anſ
    -1.13
     Conſ
    -1.12
     Jefus
    -1.12
     pleaſure
    -1.09
     Monfieur
    -1.06
     iſt
    -1.05
     Reſ
    -1.04
    POSITIVE LOGITS
     rhestr
    0.57
    rhosis
    0.55
     d
    0.54
    unhofer
    0.54
     her
    0.52
     same
    0.51
    ,
    0.51
    ;
    0.50
     the
    0.50
     D
    0.50
    Activations Density 2.479%

    No Known Activations