© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14954
    Prev
    Next
    INDEX
    Explanations

    sentence fragments with the word "and" in them

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     opérateur
    -0.59
     poffe
    -0.58
    onedDateTime
    -0.57
     szen
    -0.55
    Fordítás
    -0.54
    enderror
    -0.54
     vân
    -0.54
     fhort
    -0.53
     itſelf
    -0.53
     raiſ
    -0.53
    POSITIVE LOGITS
    Personendaten
    0.48
    TestTools
    0.43
    TagHelper
    0.42
    UIControlState
    0.42
    rildi
    0.40
    dientemente
    0.40
     HttpHeaders
    0.40
    ibatis
    0.40
    setof
    0.39
    kháu
    0.39
    Activations Density 0.572%

    No Known Activations