© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4040
    Prev
    Next
    INDEX
    Explanations

    the word "foot" in different contexts.

    oai_token-act-pair · gemini-2.0-flash

    foot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     girder
    -0.74
    __':
    -0.68
    __":
    -0.67
    chyma
    -0.67
    oneofs
    -0.67
    ugos
    -0.66
    HeaderText
    -0.65
     Mardi
    -0.65
    }$​
    -0.65
    Mardi
    -0.65
    POSITIVE LOGITS
     ExecuteAsync
    0.45
    land
    0.41
    tagHelperRunner
    0.38
    塞
    0.37
    Билгалдахарш
    0.36
     dauern
    0.36
     puestos
    0.36
    Clik
    0.36
    丹
    0.36
    print
    0.34
    Activations Density 4.207%

    No Known Activations