© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14678
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal anecdotes around food

    oai_token-act-pair · gemini-2.0-flash

    food-related expressions

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

    Punctuation

    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
     anf
    -0.44
    Linq
    -0.44
    ran
    -0.41
    に出演
    -0.40
    aparte
    -0.39
     sopr
    -0.39
    ぞ
    -0.39
    path
    -0.38
     infatti
    -0.38
    illants
    -0.38
    POSITIVE LOGITS
     Roskov
    0.87
    Personensuche
    0.76
     Yum
    0.74
    ⓧ
    0.73
    Portale
    0.73
    webElementGuid
    0.71
    "]
    0.70
    TypedDataSet
    0.69
     yum
    0.69
     Very
    0.69
    Activations Density 1.951%

    No Known Activations