© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13670
    Prev
    Next
    INDEX
    Explanations

    restaurant reviews containing menu items

    oai_token-act-pair · gemini-2.0-flash

    like

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    rungsseite
    -0.67
    #+#
    -0.64
    Хьажоргаш
    -0.59
    esModule
    -0.55
    SCRIBE
    -0.51
     发表于
    -0.51
     kasarigan
    -0.50
     isSet
    -0.49
    strconv
    -0.48
    UNGEN
    -0.47
    POSITIVE LOGITS
     GetEnumerator
    0.63
    ptonshire
    0.57
     Wicidata
    0.56
    Autoritní
    0.55
    NewUrlParser
    0.54
     Cochin
    0.53
     Sopho
    0.49
     skär
    0.49
     Carn
    0.47
    Hard
    0.47
    Activations Density 1.065%

    No Known Activations