© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12462
    Prev
    Next
    INDEX
    Explanations

    the digit 1 at the beginning of a year in the 2000s and 2010s

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    MMS
    -0.53
     vraag
    -0.53
     تانيه
    -0.52
     sveta
    -0.48
    ή
    -0.45
    əri
    -0.45
    [toxicity=0]
    -0.45
    atalos
    -0.45
    meth
    -0.45
    octet
    -0.44
    POSITIVE LOGITS
    StructEnd
    0.82
     beginnetje
    0.68
     nahilalakip
    0.66
     виправивши
    0.65
     Италијани
    0.63
    UrlResolution
    0.59
    SEGUIR
    0.57
    pats
    0.56
    sizeCache
    0.56
     ISNI
    0.56
    Activations Density 0.391%

    No Known Activations