© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4290
    Prev
    Next
    INDEX
    Explanations

    German text that has the word "habe" (have)

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     me
    -0.57
     AppCompat
    -0.49
     my
    -0.49
     track
    -0.49
     code
    -0.48
     prati
    -0.47
     used
    -0.47
    du
    -0.46
     panel
    -0.45
    Du
    -0.45
    POSITIVE LOGITS
     '\\;'
    0.88
     Efq
    0.88
     varandra
    0.83
     profondità
    0.83
     feroit
    0.82
    magitan
    0.80
     fumée
    0.79
    tiérrez
    0.78
     pioggia
    0.77
     plufieurs
    0.76
    Activations Density 1.523%

    No Known Activations