© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181730
    Prev
    Next
    INDEX
    Explanations

    beginning of sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trach
    0.36
     alkot
    0.35
    态度
    0.35
     demethyl
    0.35
     ww
    0.34
    即
    0.34
    也就是说
    0.34
     broadly
    0.34
     அதாவது
    0.34
     hled
    0.34
    POSITIVE LOGITS
     तालि
    0.40
    кін
    0.39
    чей
    0.39
    ᶤ
    0.38
     sprechen
    0.38
    vět
    0.38
    夆
    0.38
    porcion
    0.37
    muslim
    0.36
    på
    0.36
    Activations Density 0.000%

    No Known Activations